eur-lex-mcp-server
An MCP server that allows agents to search EU legislation, CJEU case law, and treaties. It resolves legal citations like CELEX and ECLI, traverses the CELLAR relationship graph for amendments and citations, and browses EuroVoc concepts for subject-based searches.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
MCP endpoint (Streamable HTTP)
https://eur-lex.caseyjhand.com/mcpWhat its tools do
7 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Resolve EU legal citations to canonical CELLAR works
- Search EU legislation and CJEU case law by various criteria
- Traverse CELLAR graph to find amendments and legal basis
- Browse EuroVoc thesaurus to resolve subject terms
Source and maintenance
Community listingRegistry 0.20.1
- Maintenance checked
Protocol and capabilities
- Server
- eur-lex-mcp-server 0.20.1
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 7 advertised
- Resources
- 1 advertised
- Resource templates
- 3 advertised
- Prompts
- 1 advertised
Server-advertised capabilities
{
"tools": {
"listChanged": true
},
"logging": {},
"prompts": {
"listChanged": true
},
"resources": {
"subscribe": true,
"listChanged": true
},
"extensions": {
"io.modelcontextprotocol/skills": {
"directoryRead": true
}
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
7 advertised
eurlex_lookup_celex — Resolve EU Legal Citation
Advertised read-onlyOpen-world
Resolve an EU legal citation — a CELEX number, ELI URI, ECLI, an OJ citation naming its act type and year (e.g. "Regulation (EU) 2016/679", "Directive 95/46/EC"), an Official Journal reference naming its issue, date, and first page (e.g. "OJ L 119, 4.5.2016, p. 1"), a Commission document number (e.g. "COM(2021) 206 final", also SEC, SWD, JOIN), or an interinstitutional procedure reference (e.g. "2021/0106(COD)", resolved to the act that initiated it) — to its canonical CELLAR work, confirming it exists before you fetch or traverse it. Returns the work URI, confirmed CELEX number, document type, date, and the ECLI of a case that carries one. A CELEX that CELLAR holds under several works resolves to the one the EUR-Lex content resolver serves. An ECLI shared by several records (a judgment and its abstract or extract, or a joined AG opinion) resolves to the primary record with the lowest CELEX. An OJ reference whose first page starts several acts, a document number CELLAR holds in several parts, and a procedure with several initiating acts return found false, the notice naming each CELEX.
eurlex_lookup_celex input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"identifier"
],
"properties": {
"identifier": {
"type": "string",
"minLength": 1,
"description": "The EU legal citation to resolve: a CELEX number (e.g. 32016R0679), a work-level ELI URI (e.g. http://data.europa.eu/eli/reg/2016/679, with or without the /oj suffix), an ECLI (e.g. ECLI:EU:C:2014:317), or an OJ citation that names its act type and year, resolved to the CELEX it names under identifier_type \"auto\": Regulation (EU) 2016/679, Regulation (EC) No 1049/2001, Directive 95/46/EC, Decision No 1313/2013/EU, Council Framework Decision 2002/584/JHA, Council Joint Action 2008/124/CFSP, Common Position 2003/444/CFSP. \"No\" before the numbers means number/year, otherwise year/number; a two-digit year is 19YY. A citation without its act type (95/46/EC) or year (Regulation No 17) is not parsed; one followed by its parenthesized OJ reference (Directive 95/46/EC (OJ L 281, 23.11.1995, p. 31)) or by the period closing a sentence resolves as the citation. An Official Journal reference resolves, also under \"auto\", to the act starting on the page it cites: OJ L 281, 23.11.1995, p. 31 (also \"of 23.11.1995\", a page range, a class letter as in OJ L 42I, OJ C, and before 1968 the series-less OJ 13, 21.2.1962, p. 204/62), the year-first OJ 1995 L 281, p. 31 or [1995] OJ L281/31, and the act-by-act OJ L, 2024/1689, 12.7.2024 or OJ C, C/2024/2664, 29.4.2024; the spellings OJ No L 281, O.J. L 281, a spaced date (23. 11. 1995), pp. 1-88, and OJ L 2024/1689 without its comma are read too, and the cited date must be the publication date. A reference without its year or first page (OJ L 281, OJ L 119/1) is not parsed. A Commission document number resolves, also under \"auto\", to the work carrying it: COM(2021) 206 final, also COM(2021)206, COM/2021/206, or COM (2021) 0206, final/2 for its second version, a two-digit year read as 19YY (COM(90) 314 final), and SEC, SWD, and JOIN numbers; a Commission decision number (C(2021) 4500 final) is not read. An interinstitutional procedure reference resolves to the act that initiated the procedure: 2021/0106(COD), also 2021/106 (COD) or 2021/0106/COD; one without its type (2021/0106) is not read. A CELEX is also read in lowercase, after a CELEX: prefix, from a EUR-Lex page URL carrying uri=CELEX:… (e.g. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32016R0679), or from a publications.europa.eu/resource/celex/ URI; an ELI over https, on the eur-lex.europa.eu host, without a scheme, with a trailing slash, or with a language segment after /oj or a date (…/oj/eng). A case number (C-131/12) names several records rather than one work and returns found false with a pointer to eurlex_get_cases."
},
"identifier_type": {
"enum": [
"celex",
"eli",
"ecli",
"auto"
],
"type": "string",
"default": "auto",
"description": "Format of the identifier. \"auto\" detects a CELEX, an ELI URI, an ECLI (by its ECLI: prefix, in any letter case), an OJ citation, an Official Journal reference, a Commission document number, or a procedure reference; \"celex\", \"eli\", or \"ecli\" forces that lookup. An OJ citation or reference, a Commission document number, and a procedure reference are recognized only under \"auto\"."
}
},
"additionalProperties": false
}eurlex_lookup_celex output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"found"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"date": {
"type": "string",
"description": "Document date in ISO 8601 format (YYYY-MM-DD). Absent when CELLAR records no real document date — none, or the 1001-01-01 it records for an undated work."
},
"ecli": {
"type": "string",
"description": "European Case Law Identifier of the case (e.g. \"ECLI:EU:C:2014:317\"), as CELLAR stores it — the resolved work's own, or the one another work holding the same CELEX records. Present for case law that carries one; absent for legislation and judicial notices."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"ambiguous_identifier",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `ambiguous_identifier`: identifier_type is \"auto\" and the identifier, after trimming, is neither an ECLI (ECLI: prefix), an ELI, a CELEX (bare, after a CELEX: prefix, or in a EUR-Lex URL), a prefixed case number, an OJ citation naming its act type and year (e.g. \"Regulation No 17\" names no year), an Official Journal reference naming its issue, year, and first page (e.g. \"OJ L 281\" names neither), a Commission document number (COM, SEC, SWD, or JOIN with its year and number; \"C(2021) 4500 final\" is none), nor a procedure reference with its type (e.g. \"2021/0106(COD)\"), so no lookup branch applies. `sparql_error`: CELLAR rejected the lookup query this call sent. The same call fails the same way again. `sparql_timeout`: The lookup ran past its time budget (retryable: CELLAR's response time varies, so a later lookup can finish), or CELLAR refused a lookup query as too costly to run (not retryable: the same query is refused again). Neither is retried within the call. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"found": {
"type": "boolean",
"description": "True when the identifier resolves to a CELLAR work; false when a well-formed CELEX, ELI, ECLI, OJ citation, Official Journal reference, Commission document number, or procedure reference matches no work in the corpus, when an OJ reference's first page starts several acts, when a document number or procedure names several works, when a procedure has no initiating act with a CELEX, or when the identifier is a case number, with a notice naming what was tried. Only an identifier_type \"auto\" value that, after trimming, is neither an ECLI, an ELI, a CELEX in any accepted form, an OJ citation naming its act type and year, an OJ reference naming its issue, year, and first page, a Commission document number, nor a procedure reference with its type raises ambiguous_identifier instead."
},
"notice": {
"type": "string",
"description": "Present only when found is false: the CELEX, ELI, ECLI, OJ reference, Commission document number, or procedure looked up, the accepted forms, and the search to use instead; for an OJ reference whose first page starts several acts, or a document number or procedure naming several works, the CELEX of each."
},
"work_uri": {
"type": "string",
"description": "CELLAR work URI (stable resource identifier)."
},
"celex_number": {
"type": "string",
"description": "Confirmed CELEX number for the resolved work."
},
"resource_type": {
"type": "string",
"description": "Human-readable document category resolved from the CDM resource type (e.g. \"Regulation\", \"Directive\", \"Judgment\"). An authority value with no known label falls back to its code (e.g. \"BUDGET\"). Absent for some works."
}
},
"additionalProperties": false
}eurlex_lookup_celex annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}eurlex_browse_subjects — Browse EuroVoc Subjects
Advertised read-onlyOpen-world
Search the EuroVoc thesaurus, resolving a keyword into concept URIs usable in the eurovoc_concept subject filter of eurlex_search_documents. CELLAR indexes no judgment, order, or Advocate General opinion of the Court of Justice or General Court by EuroVoc concept; only EFTA Court judgments carry one, so search case law by subject with eurlex_get_cases subject. Matches both preferred and alternative (non-preferred) labels, so a common synonym reaches the concept it stands for. Returns each concept URI, its preferred label in the requested language, code, broader (parent) label, and the alternative label that matched when one did. Concepts with an exact label match come first, then those whose label or one of its words starts with the keyword, then other substring matches, each group ordered by preferred label.
eurlex_browse_subjects input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"keyword"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 10000,
"minimum": 1,
"description": "Maximum number of EuroVoc concepts to return, served up to 50 per call; a larger value (up to 10,000) is served at 50 and reported in limit_clamp. Defaults to 20."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Pagination offset — number of concepts to skip. Defaults to 0. Must be below 10,000: CELLAR sorts at most 10,000 matches for one search, so pages stop at row 10,000."
},
"keyword": {
"type": "string",
"minLength": 1,
"description": "Search term matched against EuroVoc preferred and alternative concept labels (e.g. \"privacy\", \"agriculture\", \"product liability\")."
},
"language": {
"type": "string",
"default": "en",
"pattern": "^[A-Za-z]{2,3}$",
"description": "Language code for concept labels (e.g. \"en\", \"fr\", \"de\"). Case-insensitive — \"EN\" and \"en\" behave identically. Defaults to English."
}
},
"additionalProperties": false
}eurlex_browse_subjects output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"concepts",
"total",
"offset",
"has_more"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The limit that was applied to this response."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"offset_past_window",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `offset_past_window`: offset is 10,000 or more, past the last row CELLAR sorts for one search. `sparql_error`: CELLAR rejected the thesaurus search this call sent. The same call fails the same way again. `sparql_timeout`: The thesaurus search ran past its time budget (retryable: CELLAR's response time varies, so a later search can finish), or CELLAR refused it as too costly to run (not retryable: the same search is refused again). Neither is retried within the call. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"shown": {
"type": "number",
"description": "Number of concepts returned in this response."
},
"total": {
"type": "number",
"description": "Number of concepts returned in this response."
},
"notice": {
"type": "string",
"description": "Guidance for the next call: on an empty first page, the keyword and language that matched nothing and how to broaden them; on a page with more rows, the offset to continue from; on a page ending at row 10,000, that no later page can be read and how to narrow the keyword."
},
"offset": {
"type": "number",
"description": "Pagination offset used for this response."
},
"concepts": {
"type": "array",
"items": {
"type": "object",
"required": [
"concept_uri",
"pref_label"
],
"properties": {
"pref_label": {
"type": "string",
"description": "Preferred label for the concept in the requested language."
},
"concept_uri": {
"type": "string",
"description": "Full URI for the EuroVoc concept, usable in the eurovoc_concept filter."
},
"concept_code": {
"type": "string",
"description": "Numeric EuroVoc concept code."
},
"broader_label": {
"type": "string",
"description": "Preferred label of the broader (parent) concept, if available."
},
"matched_label": {
"type": "string",
"description": "Alternative (non-preferred) EuroVoc label that matched the keyword, when one did — the closest match (exact, then word start, then substring), alphabetical among equals. Absent when the keyword matched the preferred label alone."
}
},
"description": "A single EuroVoc concept with its URI, label, code, and hierarchy context.",
"additionalProperties": false
},
"description": "Matching EuroVoc concepts, exact label matches first, then word-start matches, then other substring matches, each group ordered by preferred label."
},
"has_more": {
"type": "boolean",
"description": "True only when CELLAR returned an additional valid row beyond this page. False on a page that ends at row 10,000, the last one CELLAR sorts; its notice says whether more may match."
},
"truncated": {
"type": "boolean",
"description": "True when an additional CELLAR row proves more concepts exist beyond this page."
},
"limit_clamp": {
"type": "object",
"required": [
"requested",
"applied"
],
"properties": {
"applied": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit served: the per-call maximum."
},
"requested": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit the call asked for."
}
},
"description": "Present only when limit exceeded the per-call maximum: the value asked for and the value served. The response follows the applied value.",
"additionalProperties": false
},
"next_offset": {
"type": "number",
"description": "Offset for the next page. Present only when has_more is true."
}
},
"additionalProperties": false
}eurlex_browse_subjects annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}eurlex_search_documents — Search EU Documents
Advertised read-onlyOpen-world
Search EU legislation, treaties, and preparatory acts across the CELLAR corpus by document type, date range, EuroVoc subject, author institution, and in-force status. Keyword matches English titles and CELEX strings only — there is no full-text body search. Corrigenda are excluded by default so primary acts fill the page (set include_corrigenda to include them). Returns a page of CELEX numbers, work URIs, type labels, dates, and titles, newest first, each flagged with is_consolidated and is_corrigendum. At least one filter is required.
eurlex_search_documents input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 10000,
"minimum": 1,
"description": "Maximum number of results to return, served up to 100 per call; a larger value (up to 10,000) is served at 100 and reported in limit_clamp. Defaults to 20."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Pagination offset — number of results to skip. Defaults to 0. Must be below 10,000: CELLAR sorts at most 10,000 matches for one search, so pages stop at row 10,000; narrow with a date_from/date_to window to reach older documents."
},
"date_to": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "End date in ISO 8601 format (YYYY-MM-DD)."
}
],
"description": "End of date range (YYYY-MM-DD), matched against document date. Omit for no upper bound."
},
"keyword": {
"type": "string",
"description": "Keyword matched against English document titles via the full-text index (multi-word input is treated as a phrase), and against CELEX numbers. A keyword that is a whole CELEX (e.g. 32016R0679) matches that document, its numbered siblings (…(01) to …(20)), and for case law its _INF, _RES, _SUM, and _EXT records, plus its corrigenda (…R(01) to …R(20), and any work recorded as correcting it) when include_corrigenda is set. A partial CELEX that opens with the sector and year (02016R0679), the year and type letters (2016R0679), or type letters followed by the number (R0679, J0131) matches every CELEX that holds it at that position, consolidated versions included; an OJ C fragment of a year, a slash, and at least four characters of the number (2024/01469, C/2024/0146) matches every CELEX holding it; one with a shorter number (2017/111) or opening with letters not followed by a digit (R(01), ROU_2024) tests every CELEX and can take tens of seconds; a bare year (2016) or a fragment opening mid-year or mid-number (016R0679, 0679, 0679R) matches titles only. A keyword with no digit, or with a character no CELEX holds (a space, a period), matches titles only. A keyword with no letter or digit is rejected."
},
"in_force": {
"type": "boolean",
"description": "Restrict by in-force status: true returns only acts currently in force; false returns acts not in force — repealed, expired, or not yet in force (eurlex_get_document names which, where CELLAR records one). Either way the act must carry the in-force property, which a minority of works do. Omit to return all regardless of in-force status."
},
"date_from": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Start date in ISO 8601 format (YYYY-MM-DD)."
}
],
"description": "Start of date range (YYYY-MM-DD), matched against document date. Omit for no lower bound."
},
"document_type": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"enum": [
"REG",
"DIR",
"DEC",
"TREATY",
"JUDG",
"OPIN_AG",
"PROP",
"REC"
],
"type": "string",
"description": "Document type: REG=Regulation, DIR=Directive, DEC=Decision, TREATY=Treaty, JUDG=Judgment, OPIN_AG=AG Opinion, PROP=Proposal, REC=Recommendation."
}
],
"description": "Document category: REG=Regulations, DIR=Directives, DEC=Decisions, TREATY=Treaties, JUDG=Judgments, OPIN_AG=AG Opinions, PROP=Proposals, REC=Recommendations. Each category includes its explicit CELLAR authority variants (for example, delegated and implementing regulations). Omit to search all types. Consolidated texts are excluded unless include_consolidated is true. Search case law by court, case number, or subject with eurlex_get_cases."
},
"eurovoc_concept": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"description": "EuroVoc concept URI (e.g. http://eurovoc.europa.eu/2828)."
}
],
"description": "EuroVoc concept URI to filter by subject (e.g. http://eurovoc.europa.eu/2828), obtained from eurlex_browse_subjects. Only EuroVoc concept URIs are accepted; https://eurovoc.europa.eu/… and an upper-case host are read as the http://eurovoc.europa.eu/… form CELLAR stores. CELLAR indexes no judgment, order, or Advocate General opinion of the Court of Justice or General Court by EuroVoc concept; only EFTA Court judgments carry one. Search case law by subject with eurlex_get_cases subject. Omit for no subject filter."
},
"author_institution": {
"type": "string",
"description": "Author name (e.g. \"European Parliament\", \"Council\", \"European Commission\", \"Supremo Tribunal de Justiça\"), matched as a phrase against English authority labels or national-court names — the labels eurlex_get_document reports in author_institution(s), member states and MEPs included."
},
"include_corrigenda": {
"type": "boolean",
"default": false,
"description": "Include corrigenda — separate correction works, co-typed CORRIGENDUM alongside the base type of the act they correct, carrying a \"…R(nn)\" CELEX and usually no English title. Default false: they are excluded so primary acts fill the page. Every returned row is tagged is_corrigendum."
},
"include_consolidated": {
"type": "boolean",
"default": false,
"description": "When true and document_type is set, also match consolidated texts whose basic act belongs to that document category. No effect when document_type is omitted. Consolidated rows are always tagged is_consolidated: true."
}
},
"additionalProperties": false
}eurlex_search_documents output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"documents",
"total",
"offset",
"has_more",
"query_echo"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The limit that was applied to this page."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"offset_past_window",
"no_filters",
"invalid_date_range",
"invalid_author_institution",
"invalid_keyword",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `offset_past_window`: offset is 10,000 or more, past the last row CELLAR sorts for one search. `no_filters`: No effective narrowing filter was supplied — an unfiltered search would scan the entire corpus. `invalid_date_range`: date_from or date_to is not a real calendar date, or date_from falls after date_to. `invalid_author_institution`: author_institution holds no letters or digits, so it can name no institution. `invalid_keyword`: keyword holds no letters or digits, so no title and no CELEX can match it. `sparql_error`: CELLAR rejected the search it was sent: a filter combination its query planner cannot compile. The same call fails the same way again. `sparql_timeout`: The search ran past its time budget (retryable: CELLAR's response time varies, so a later search can finish), or CELLAR refused it as too costly to run (not retryable: the same search is refused again). Neither is retried within the call. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"shown": {
"type": "number",
"description": "Number of documents returned in this page."
},
"total": {
"type": "number",
"description": "Number of documents returned in this page (not a corpus-wide count)."
},
"notice": {
"type": "string",
"description": "Guidance for the next call: on an empty first page, the filters that matched nothing and how to broaden them, or, for eurovoc_concept with document_type JUDG or OPIN_AG, how to search case law by subject with eurlex_get_cases instead; on a page with more rows, the offset to continue from; on a page ending at row 10,000, that no later page can be read and the closed date_from/date_to window that continues past it."
},
"offset": {
"type": "number",
"description": "Pagination offset used for this response."
},
"has_more": {
"type": "boolean",
"description": "True only when CELLAR returned an additional valid row beyond this page. False on a page that ends at row 10,000, the last one CELLAR sorts; its notice says whether more may match."
},
"documents": {
"type": "array",
"items": {
"type": "object",
"required": [
"work_uri",
"celex_number",
"is_consolidated",
"is_corrigendum"
],
"properties": {
"date": {
"type": "string",
"description": "Document date in ISO 8601 format (YYYY-MM-DD). Absent when CELLAR records no real document date — none, or the 1001-01-01 it records for an undated work; such documents sort last."
},
"title": {
"type": "string",
"description": "English expression title where available; absent for many older works and judgments."
},
"work_uri": {
"type": "string",
"description": "CELLAR work URI (stable resource identifier)."
},
"celex_number": {
"type": "string",
"description": "CELEX identifier for the work."
},
"resource_type": {
"type": "string",
"description": "Human-readable document type label (e.g. \"Regulation\", \"Directive\"). Works with several resource-types (e.g. corrigenda) list all, comma-separated. Absent for some older works."
},
"is_corrigendum": {
"type": "boolean",
"description": "True when this work carries the CORRIGENDUM resource-type — a correction to another act rather than a primary act. Only ever true when include_corrigenda is set, since corrigenda are excluded by default."
},
"is_consolidated": {
"type": "boolean",
"description": "True when this CELEX is a consolidated version (sector 0, e.g. 02016R0679-20160504) — a point-in-time text that incorporates amendments — rather than a base or amending act."
}
},
"description": "A single EU legislative work with its CELEX number, type, and date.",
"additionalProperties": false
},
"description": "Matching EU documents ordered by date descending, then by CELEX number ascending among documents sharing a date, so pages are stable across calls."
},
"truncated": {
"type": "boolean",
"description": "True when an additional CELLAR row proves more documents exist beyond this page."
},
"query_echo": {
"type": "object",
"required": [
"include_consolidated",
"include_corrigenda"
],
"properties": {
"date_to": {
"type": "string",
"description": "End date filter applied."
},
"keyword": {
"type": "string",
"description": "Keyword filter applied."
},
"in_force": {
"type": "boolean",
"description": "In-force filter applied."
},
"date_from": {
"type": "string",
"description": "Start date filter applied."
},
"document_type": {
"type": "string",
"description": "Document type filter applied."
},
"eurovoc_concept": {
"type": "string",
"description": "EuroVoc concept URI filter applied, in the http://eurovoc.europa.eu/ form it was matched as."
},
"author_institution": {
"type": "string",
"description": "Author institution filter applied."
},
"include_corrigenda": {
"type": "boolean",
"description": "Effective include_corrigenda value after the false default is applied — whether corrigenda were admitted alongside primary acts. Always present, since the default shapes which records can appear."
},
"include_consolidated": {
"type": "boolean",
"description": "Effective include_consolidated value after the false default is applied — whether consolidated texts whose basic act belongs to the document_type category were included. Always present, since the default shapes which records can appear; has effect only when document_type is set."
}
},
"description": "Echo of filters applied to this search. Useful for diagnosing empty results.",
"additionalProperties": false
},
"limit_clamp": {
"type": "object",
"required": [
"requested",
"applied"
],
"properties": {
"applied": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit served: the per-call maximum."
},
"requested": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit the call asked for."
}
},
"description": "Present only when limit exceeded the per-call maximum: the value asked for and the value served. The response follows the applied value.",
"additionalProperties": false
},
"next_offset": {
"type": "number",
"description": "Offset for the next page. Present only when has_more is true."
}
},
"additionalProperties": false
}eurlex_search_documents annotations
{
"readOnlyHint": true,
"openWorldHint": true
}eurlex_get_cases — Search CJEU/GC Case Law
Advertised read-onlyOpen-world
Search CJEU and General Court case law — judgments, orders, and Advocate General opinions and views — by case number, court, case type, member state, procedure type and outcome, subject, keyword, and date range. A case number reaches every judgment, order, AG opinion, and AG view filed under it. By default only these primary records are returned; derivative judicial information notices, case abstracts, summaries, and corrigenda are excluded so distinct cases fill the page (set include_derivative to include them). Keyword matches English case titles (which carry party names) and CELEX strings; there is no full-text body search. member_state, procedure_type, outcome, and subject match the facts CELLAR records on each case, so a case it records none of a filtered fact for never matches. Returns each case with its CELEX number (whose sixth character names the court: C, T, or F), work URI, ECLI, date, and type; where CELLAR records them, its countries, procedure types with outcome, subjects, and procedure languages; and — parsed from the title where present — the formation, Advocate General, parties, referring court, subject matter, and case reference. The raw CELLAR title is returned only when those fields do not capture all of it.
eurlex_get_cases input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"court": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"enum": [
"CJEU",
"GC"
],
"type": "string",
"description": "CJEU (C) = Court of Justice of the EU, GC (T) = General Court."
}
],
"description": "Court filter, by the court letter at position 6 of the CELEX: CJEU (C) = Court of Justice of the EU, GC (T) = General Court. It does not narrow by record type: every primary record the court filed matches, and its derivative records (notices, abstracts, summaries, corrigenda) join only under include_derivative. Omit to search every court."
},
"limit": {
"type": "integer",
"default": 20,
"maximum": 10000,
"minimum": 1,
"description": "Maximum number of results to return, served up to 100 per call; a larger value (up to 10,000) is served at 100 and reported in limit_clamp. Defaults to 20."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Pagination offset — number of results to skip. Defaults to 0. Must be below 10,000: CELLAR sorts at most 10,000 matches for one search, so pages stop at row 10,000; narrow with a date_from/date_to window to reach older cases."
},
"date_to": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "End date in ISO 8601 format (YYYY-MM-DD)."
}
],
"description": "End of date range in ISO 8601 format (YYYY-MM-DD). Leave blank or omit for no upper bound."
},
"keyword": {
"type": "string",
"description": "Keyword matched against English case titles via the full-text index (multi-word input is treated as a phrase), and against CELEX numbers. A keyword that is a whole CELEX (e.g. 62023CO0097) matches that record, its numbered siblings (…(01) to …(20)), its _INF, _RES, _SUM, and _EXT records, and its corrigenda, with notices, abstracts, summaries, and corrigenda still joining only under include_derivative; for every record filed under a case, use case_number. A partial CELEX that opens with the sector and year (62013CJ), the year and type letters (2013CJ0131), or type letters followed by the number (CJ0131, J0131) matches every CELEX that holds it at that position; one opening with letters not followed by a digit (R(01)) tests every CELEX and can take tens of seconds; a bare year (2013) or a fragment opening mid-year or mid-number (013CJ0131, 0131) matches titles only. A keyword with no digit, or with a character no CELEX holds (a space, a period), matches titles only. A keyword with no letter or digit is rejected."
},
"outcome": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"enum": [
"successful",
"unfounded",
"inadmissible",
"decision_unnecessary"
],
"type": "string",
"description": "successful, unfounded, inadmissible, or decision_unnecessary."
}
],
"description": "Outcome CELLAR records with the procedure: successful, unfounded, inadmissible, or decision_unnecessary. With procedure_type, both hold on the same procedure (annulment with successful finds annulment actions that succeeded); alone, any procedure with that outcome. Preliminary references rarely record one. Omit to search all."
},
"subject": {
"type": "string",
"description": "Subject phrase matched against the English labels of CELLAR's case-law subject classification: the search covers every subject whose label contains each word of the phrase, in any case and also inside a longer word (\"trade mark\" matches \"Trade marks\", \"personal data\" \"Protection of personal data\", \"tax\" also \"Taxation\"). query_echo.subject_labels names the subjects matched; each row lists its own in subjects. This is not the title's subject_matter keywords. A phrase matching no label returns an empty page with a notice. Leave blank or omit to search every subject."
},
"case_type": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"enum": [
"judgment",
"order",
"ag_opinion"
],
"type": "string",
"description": "judgment, order (procedural decision), or ag_opinion (Advocate General opinion or view)."
}
],
"description": "Case type: judgment, order (procedural decision), or ag_opinion (Advocate General opinion or view). Omit to search all."
},
"date_from": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Start date in ISO 8601 format (YYYY-MM-DD)."
}
],
"description": "Start of date range in ISO 8601 format (YYYY-MM-DD). Leave blank or omit for no lower bound."
},
"case_number": {
"type": "string",
"description": "Number of a single case: C-{num}/{year} (Court of Justice), T-{num}/{year} (General Court), or F-{num}/{year} (Civil Service Tribunal), e.g. C-131/12. Also accepts the case_reference form (\"Case C-97/23 P.\"), any procedural suffix after the year (P, R, PPU, …), and a pre-1989 Court of Justice number with no prefix (26/62). A value naming more than one case (\"C-131/12 and C-132/12\") is rejected; search each separately. Matches the judgments, orders, AG opinions, and other primary records filed under that number; derivative records (notices, abstracts, summaries, corrigenda) join only under include_derivative. Numbered Opinions and Rulings of the Court of Justice (\"Opinion 2/13\", \"Ruling 1/78\") are not reached by a case number; look one up by its CELEX (e.g. 62013CV0002). A value made only of CELEX characters is matched as a CELEX substring instead, case-insensitively: one opening with the sector and year (62014CJ0362), the year and both letters (2013CJ0131), or both letters and the number (CJ0131) is answered from the CELEX index; any other (12CJ0131, 0131) tests every CELEX and can take tens of seconds."
},
"member_state": {
"type": "string",
"description": "Member state the case originates in, as CELLAR records it: the referring court's state on a preliminary reference, the defendant state on an action for failure to fulfil obligations, the applicant's state (or the member state party) on a direct action. A member state as its ISO 3166-1 alpha-3 code (DEU, GRC, GBR for the United Kingdom) or two-letter code (DE; EL or GR for Greece; UK or GB), in any case: the 27 member states plus the United Kingdom. Cases CELLAR records no country for, Civil Service Tribunal staff cases among them, never match. Leave blank or omit to search every state."
},
"procedure_type": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"enum": [
"preliminary_ruling",
"annulment",
"staff_case",
"appeal",
"failure_to_fulfil_obligations",
"damages",
"interim_measures",
"appeal_against_penalty",
"failure_to_act",
"arbitration_clause"
],
"type": "string",
"description": "preliminary_ruling, annulment, staff_case, appeal, failure_to_fulfil_obligations, damages, interim_measures, appeal_against_penalty, failure_to_act, or arbitration_clause."
}
],
"description": "Procedure type, as CELLAR classifies the case: preliminary_ruling (urgent references included), annulment, staff_case, appeal, failure_to_fulfil_obligations, damages, interim_measures, appeal_against_penalty, failure_to_act, or arbitration_clause. A case can carry several: an appeal also carries the action appealed. Each row lists its own in procedure_types. Omit to search all."
},
"include_derivative": {
"type": "boolean",
"default": false,
"description": "Include derivative sector-6 records — judicial information notices, case abstracts, case summaries, and corrigenda — alongside primary judgments, orders, AG opinions, and AG views. Default false: these are excluded so distinct primary cases fill the page. Ignored when case_type is set (that path already requires the selected primary type family). Has no effect beside member_state, procedure_type, outcome, or subject, since derivative records carry none of those facts."
}
},
"additionalProperties": false
}eurlex_get_cases output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"cases",
"total",
"offset",
"has_more",
"query_echo"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The limit that was applied to this page."
},
"cases": {
"type": "array",
"items": {
"type": "object",
"required": [
"work_uri",
"celex_number"
],
"properties": {
"date": {
"type": "string",
"description": "Judgment/opinion date in ISO 8601 format. Absent when CELLAR records no real document date — none, or the 1001-01-01 it records for an undated work; such cases sort last."
},
"ecli": {
"type": "string",
"description": "European Case Law Identifier, the citation form of the record (e.g. \"ECLI:EU:C:2014:317\"); eurlex_lookup_celex resolves one back to its CELEX. Absent for judicial notices and the few records that carry none."
},
"title": {
"type": "string",
"description": "Raw English expression title as stored in CELLAR, a \"#\"-delimited string (court, formation and date; parties; referral; subject matter; case reference). Present only when the parsed fields do not capture all of it: a segment the parser could not place, a judgment or order published by extracts (\"(Extracts)\"), a leading date that differs from date, or a title with no \"#\". Absent when the parse is complete, and for records with no English title."
},
"parties": {
"type": "string",
"description": "Parties to the case, parsed from the title (e.g. \"WhatsApp Ireland Ltd v European Data Protection Board.\"). Absent when the title carries no parties segment (e.g. AG opinions)."
},
"subjects": {
"type": "array",
"items": {
"type": "string",
"description": "English subject label, e.g. \"Protection of personal data\"."
},
"description": "Subjects of CELLAR's case-law subject classification, as English labels, sorted; what subject matches. A controlled vocabulary, unlike the title's subject_matter keywords. Absent when CELLAR records none."
},
"work_uri": {
"type": "string",
"description": "CELLAR work URI."
},
"countries": {
"type": "array",
"items": {
"type": "string",
"description": "ISO 3166-1 alpha-3 country code, e.g. \"BGR\"."
},
"description": "Countries CELLAR records the case as originating in, as ISO 3166-1 alpha-3 codes, sorted: the referring court's state on a preliminary reference, the defendant state on an action for failure to fulfil obligations, the applicant's state on a direct action. Member states, the values member_state takes, bar a few older direct actions by non-EU applicants. Absent when CELLAR records none, as on Civil Service Tribunal staff cases."
},
"formation": {
"type": "string",
"description": "Formation that decided, from the title's leading segment, verbatim (e.g. \"Grand Chamber\", \"Full Court\", \"Fourth Chamber, Extended Composition\"), or \"President\", \"Vice-President\", or \"President of the Second Chamber\" for an order issued by that office. Absent when the title names none, as older \"Judgment of the Court of …\" titles do."
},
"celex_number": {
"type": "string",
"description": "CELEX identifier for the case (e.g. 62024CJ0629)."
},
"display_title": {
"type": "string",
"description": "Clean human-readable title for display — the parties for a contested case (e.g. \"Google Spain SL v AEPD\"), or the court/AG descriptor when a case has no named parties. Parsed from the English title; absent when the record has none or its title carries no \"#\" segments."
},
"resource_type": {
"type": "string",
"description": "Human-readable case type label (e.g. \"Judgment\", \"Order\", \"AG Opinion\"). Cases with several resource-types (e.g. corrigenda) list all, comma-separated. Absent for some older cases."
},
"case_reference": {
"type": "string",
"description": "Case reference parsed from the title (e.g. \"Case C-97/23 P.\"). Absent when the title carries no case-reference segment."
},
"subject_matter": {
"type": "string",
"description": "Subject-matter keyword summary parsed from the title — the legal topics and provisions at issue. Free text, unlike subjects, CELLAR's subject classification. Absent when the title carries no subject-matter segment."
},
"procedure_types": {
"type": "array",
"items": {
"type": "string",
"description": "English procedure label, e.g. \"Action for annulment - successful\"."
},
"description": "Procedure types CELLAR classifies the case under, as English labels with the outcome where recorded (\"Reference for a preliminary ruling\", \"Appeal - unfounded\"), sorted; what procedure_type and outcome match. An appeal also lists the action appealed. Absent when CELLAR records none."
},
"referring_court": {
"type": "string",
"description": "National court that referred a preliminary ruling, from the title's referral segment (e.g. \"Audiencia Nacional\", or \"Tariefcommissie - Netherlands\" in older titles). Absent on direct actions and appeals."
},
"advocate_general": {
"type": "string",
"description": "Advocate General who delivered the opinion, from an AG opinion title (e.g. \"Jääskinen\"). Absent on judgments and orders."
},
"procedure_languages": {
"type": "array",
"items": {
"type": "string",
"description": "Two-letter EUR-Lex language code, e.g. \"BG\"."
},
"description": "Languages of the case, as the two-letter codes eurlex_get_document takes as language, sorted. Absent when CELLAR records none, as on about half of the Court of Justice AG opinions and records dated before 1990."
}
},
"description": "A single CJEU or General Court case law record.",
"additionalProperties": false
},
"description": "Matching case law records ordered by date descending, then by CELEX number ascending among records sharing a date, so pages are stable across calls."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"offset_past_window",
"invalid_date_range",
"invalid_case_number",
"invalid_keyword",
"invalid_subject",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `offset_past_window`: offset is 10,000 or more, past the last row CELLAR sorts for one search. `invalid_date_range`: date_from or date_to is not a real calendar date, or date_from falls after date_to. `invalid_case_number`: case_number is not a recognizable case number and holds characters no CELEX contains, names more than one case (e.g. \"C-131/12 and C-132/12\"), or is a prefix-less number dated outside 1953–1988. `invalid_keyword`: keyword holds no letters or digits, so no case title and no CELEX can match it. `invalid_subject`: subject holds no letters or digits, so no subject label can match it. `sparql_error`: CELLAR rejected the search it was sent: a filter combination its query planner cannot compile. The same call fails the same way again. `sparql_timeout`: The search ran past its time budget (retryable: CELLAR's response time varies, so a later search can finish), or CELLAR refused it as too costly to run (not retryable: the same search is refused again). Neither is retried within the call. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"shown": {
"type": "number",
"description": "Number of cases returned in this page."
},
"total": {
"type": "number",
"description": "Number of cases returned in this page (not a corpus-wide count)."
},
"notice": {
"type": "string",
"description": "Guidance for the next call: on an empty first page, the filters that matched nothing and how to broaden them; when subject matched no subject label, that no case was searched; on a page with more rows, the offset to continue from; on a page ending at row 10,000, that no later page can be read and the closed date_from/date_to window that continues past it."
},
"offset": {
"type": "number",
"description": "Pagination offset used for this response."
},
"has_more": {
"type": "boolean",
"description": "True only when CELLAR returned an additional valid row beyond this page. False on a page that ends at row 10,000, the last one CELLAR sorts; its notice says whether more may match."
},
"truncated": {
"type": "boolean",
"description": "True when an additional CELLAR row proves more cases exist beyond this page."
},
"query_echo": {
"type": "object",
"required": [
"include_derivative"
],
"properties": {
"court": {
"type": "string",
"description": "Court filter applied."
},
"date_to": {
"type": "string",
"description": "End date filter applied."
},
"keyword": {
"type": "string",
"description": "Keyword filter applied."
},
"outcome": {
"type": "string",
"description": "Outcome filter applied."
},
"subject": {
"type": "string",
"description": "Subject phrase applied."
},
"case_type": {
"type": "string",
"description": "Case type filter applied."
},
"date_from": {
"type": "string",
"description": "Start date filter applied."
},
"case_number": {
"type": "string",
"description": "Case number filter applied."
},
"member_state": {
"type": "string",
"description": "Member-state filter applied, as its ISO 3166-1 alpha-3 code."
},
"celex_fragment": {
"type": "string",
"description": "CELEX pattern matched for case_number: year, court letter, and zero-padded case number, with * standing for any document letter that court files under a case number (e.g. \"2023C*0097\" reaches 62023CJ0097, 62023CO0097, and 62023CC0097). Absent when case_number was matched as a raw CELEX substring."
},
"procedure_type": {
"type": "string",
"description": "Procedure type filter applied."
},
"subject_labels": {
"type": "array",
"items": {
"type": "string",
"description": "English subject label."
},
"description": "English labels of the subjects the subject phrase matched, sorted: the subjects the search was narrowed to. Empty when the phrase matched none, and then no case was searched. Absent when no subject was given."
},
"include_derivative": {
"type": "boolean",
"description": "Effective include_derivative value after the false default is applied — whether derivative sector-6 records (notices, abstracts, summaries, corrigenda) were admitted alongside primary cases. Always present, since the default shapes which records can appear."
}
},
"description": "Echo of filters applied to this search. Useful for diagnosing empty results.",
"additionalProperties": false
},
"limit_clamp": {
"type": "object",
"required": [
"requested",
"applied"
],
"properties": {
"applied": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit served: the per-call maximum."
},
"requested": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit the call asked for."
}
},
"description": "Present only when limit exceeded the per-call maximum: the value asked for and the value served. The response follows the applied value.",
"additionalProperties": false
},
"next_offset": {
"type": "number",
"description": "Offset for the next page. Present only when has_more is true."
}
},
"additionalProperties": false
}eurlex_get_cases annotations
{
"readOnlyHint": true,
"openWorldHint": true
}eurlex_get_document — Get EU Document
Advertised read-onlyOpen-world
Fetch the metadata and full text of an EU act or case-law record by CELEX number, ELI URI, or work URI. Returns structured metadata (title, date, type, ELI, Official Journal reference, typed dates of effect, transposition deadlines, author institution, Advocates General, legal basis, EuroVoc subjects, in-force status and, for an act not in force, its repealing acts, end of validity, or pending entry into force; the legislative procedures the act belongs to, each with its status — adopted, withdrawn, pending, or not adopted — and the acts it produced; for case law, the ECLI, the formation, referring court, subject matter, and case reference parsed from the title, and the countries, procedure types with their outcome, subjects, and procedure languages CELLAR records) plus the body as HTML, Markdown, or Formex4 XML, defaulting to English with automatic fallback. Every body returned in one call is capped at 100,000 characters — paged and full windows page onward with offset/limit; use outline: true for a heading map and select to pull specific articles, chapters, recitals, or annexes of an act, or the headed sections and operative part of a judgment or order, reading a selected section on its own from the offset and chars in selected_sections.
eurlex_get_document input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"default": 25000,
"minimum": 1,
"description": "Maximum characters to return in this window (\"paged\" mode only; select ignores it). Default 25000; a window holds at most 100000 characters, so a larger value is served at 100000 and reported in limit_clamp. Follow has_more and the returned offsets until false to reconstruct the complete body."
},
"format": {
"enum": [
"html",
"xml",
"markdown"
],
"type": "string",
"default": "html",
"description": "Content format: \"html\" for the act text as served by EUR-Lex (default), \"markdown\" for that HTML converted to clean Markdown server-side, or \"xml\" for Formex4 structured XML."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Character offset into the body where the returned window starts (\"paged\" mode only). Page forward by setting offset = content_offset + content_chars_returned from the previous call. Offsets are format-specific: an offset is only valid against the same format it was measured in — keep format constant when paging."
},
"select": {
"type": "object",
"properties": {
"annexes": {
"type": "string",
"description": "Comma-separated annex numbers or letters, e.g. \"I,II\". \"ANNEX\" alone (any case, or the served language's annex word, e.g. \"Anhang\") selects an act's lone unnumbered annex; on an act whose annexes are numbered it misses, and the notice names their numbers."
},
"articles": {
"type": "string",
"description": "Comma-separated article numbers, e.g. \"1,5,17\"."
},
"chapters": {
"type": "string",
"description": "Comma-separated chapter numbers, Roman or Arabic, e.g. \"I,IV\" or \"1,4\"."
},
"headings": {
"type": "string",
"description": "Case law: comma-separated positions of section headings, as numbered in the outline, e.g. \"2\" or \"1,4\". A section runs to the next heading or the operative part."
},
"recitals": {
"type": "string",
"description": "Comma-separated recital numbers, e.g. \"1,10\"."
},
"operative_part": {
"type": "boolean",
"description": "Case law: true to return a judgment's or order's operative part (the ruling) to the end of the body: from its opening words (\"On those grounds, …\") in a modern body, from the \"Operative part\" section in a legacy one."
}
},
"description": "Return only the text of specific sections by type and number, instead of a raw character window (Roman and Arabic numbers are equivalent; a number may carry an English kind word or one in the language served, e.g. \"Article 5\", \"Artikel 5\", \"5. cikk\"). For case law, select headed sections by position or the operative part. An act's section runs to its next heading, and its last article, section, and chapter stop where the enacting terms end: the closing formula, signatures, and footnotes after them (and in xml the annexes) belong to no section, nor do the notes closing a consolidated text — read those by paging on from the section's end. Sections are located in the body of the requested format, so pair select with the same format used for any outline. A section inside another selected section (an article in a selected chapter) is returned once, within the enclosing one. A section that cannot be located — including a number that appears only in text an amending act inserts into another act — is reported in selection.missed with no wrong text returned. offset and limit do not apply: the joined sections are capped at 100000 characters with no continuation, and each section stays readable on its own from its offset and chars in selected_sections. Ignored when outline is true or in content_mode \"metadata_only\"."
},
"eli_uri": {
"type": "string",
"description": "Work-level ELI URI of the act to fetch (e.g. http://data.europa.eu/eli/reg/2016/679, with or without the /oj suffix). Provide exactly one of celex_number, eli_uri, or work_uri."
},
"outline": {
"type": "boolean",
"default": false,
"description": "Return a structural outline of the act — chapters, sections, articles, annexes, and the preamble's recitals as a heading list, each with its character offset — instead of body text. The recitals appear as one entry spanning the run (e.g. \"Recitals 1–173\") at the first recital's offset unless include_recitals is true. Headings of text an amending act inserts into another act are not listed. For case law, the outline lists each top-level section heading (\"Legal context\", \"Costs\") and, for a judgment or order, the operative part (the ruling). Read a section by paging with its offset, keeping the same format: outline offsets are measured in the requested format's body and land in the wrong place under any other format. Ignores offset/limit and select; no detectable structure returns an empty outline. Not applied in content_mode \"metadata_only\"."
},
"resolve": {
"enum": [
"as_requested",
"current_consolidated"
],
"type": "string",
"default": "as_requested",
"description": "Which version to serve. \"as_requested\" (default) returns the exact CELEX requested; \"current_consolidated\" serves the newest consolidated version in effect of the requested act — or, for a consolidated CELEX, of its base act — echoing the request in requested_celex, and is a no-op when none exists (with a notice when the act's only consolidated versions are dated in the future). Either way, is_superseded / current_consolidated_celex / consolidated_as_of describe the text served."
},
"language": {
"type": "string",
"default": "EN",
"pattern": "^(?:[Ee][Nn]|[Ff][Rr]|[Dd][Ee]|[Ee][Ss]|[Ii][Tt]|[Pp][Ll]|[Pp][Tt]|[Nn][Ll]|[Cc][Ss]|[Dd][Aa]|[Ee][Ll]|[Ee][Tt]|[Ff][Ii]|[Hh][Uu]|[Ll][Tt]|[Ll][Vv]|[Mm][Tt]|[Rr][Oo]|[Ss][Kk]|[Ss][Ll]|[Ss][Vv]|[Bb][Gg]|[Hh][Rr]|[Gg][Aa])$",
"description": "One of the 24 supported two-letter EUR-Lex language codes (e.g. EN, FR, DE), accepted case-insensitively and normalized to uppercase. Defaults to EN, and falls back to EN if the requested language is unavailable."
},
"work_uri": {
"type": "string",
"description": "CELLAR work resource URI to fetch (e.g. http://publications.europa.eu/resource/cellar/3e485e15-11bd-11e6-ba9a-01aa75ed71a1) — the form returned by eurlex_lookup_celex, eurlex_get_relations, and eurlex_search_documents. A work carrying several CELEX numbers (a national implementing measure, one per directive it was notified against) is served under its lowest, with a notice giving the count; each names the same document, so pass celex_number to serve a specific one. An expression or manifestation URI (…/cellar/{id}.0006, ….0006.03) is served as the work it belongs to, with a notice. Provide exactly one of celex_number, eli_uri, or work_uri."
},
"celex_number": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"pattern": "^[0-9A-Z][0-9A-Z()/_-]{5,}$",
"description": "CELEX number of the act (e.g. 32016R0679 for GDPR). Surrounding whitespace is trimmed and the value is uppercased before validation."
}
],
"description": "CELEX number of the act to fetch (e.g. 32016R0679 for GDPR). Provide exactly one of celex_number, eli_uri, or work_uri."
},
"content_mode": {
"enum": [
"metadata_only",
"paged",
"full"
],
"type": "string",
"default": "paged",
"description": "How much of the body to return. \"paged\" (default) returns an offset/limit window; \"full\" requests from the start and returns at most 100000 characters with continuation metadata when more exists; \"metadata_only\" skips the content fetch. offset and limit apply only to \"paged\"."
},
"include_recitals": {
"type": "boolean",
"default": false,
"description": "List every recital as its own outline entry, with its own offset, instead of one entry for the run. Applies only when outline is true; select reaches a single recital either way."
}
},
"additionalProperties": false
}eurlex_get_document output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"celex_number",
"content_mode",
"content_available",
"content_status",
"has_more",
"language",
"content_format"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Maximum body characters allowed in the window."
},
"eli": {
"type": "string",
"description": "European Legislation Identifier of the work served (e.g. \"http://data.europa.eu/eli/reg/2016/679/oj\"); a consolidated text carries its own point-in-time ELI (e.g. \"http://data.europa.eu/eli/reg/2016/679/2016-05-04\"), a corrigendum its own. Absent when CELLAR records none, as for case law, proposals, and national measures."
},
"date": {
"type": "string",
"description": "Document date in ISO 8601 format (YYYY-MM-DD). Absent when CELLAR records no real document date — none, or the 1001-01-01 it records for an undated work."
},
"ecli": {
"type": "string",
"description": "European Case Law Identifier of a case-law record (e.g. \"ECLI:EU:C:2014:317\"), as eurlex_lookup_celex reports it: the work's own, or the lowest another work holding the same CELEX records. Absent for legislation."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"invalid_identifier_args",
"not_found",
"content_challenge",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `invalid_identifier_args`: None of celex_number, eli_uri, or work_uri was provided, or more than one was. `not_found`: The CELEX, ELI, or work URI resolves to no fetchable work — the work is absent from the corpus, or the CELLAR work (for an expression or manifestation URI, the work it belongs to) carries no CELEX number. `content_challenge`: The primary content response is an AWS WAF bot-challenge interstitial rather than legal text. `sparql_error`: CELLAR rejected a query this call sent to resolve the identifier or read its metadata. The same call fails the same way again. `sparql_timeout`: A query this call sent to CELLAR ran past the time budget the call's queries share (retryable: CELLAR's response time varies, so a later call can finish), or CELLAR refused it as too costly to run (not retryable: the same query is refused again). Neither is retried within the call. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"shown": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of body characters returned."
},
"title": {
"type": "string",
"description": "Document title in the language the body is served in (see language), or in English when CELLAR records no title in that language. Case law is titled in English whatever the language, parsed from its English CELLAR title: the parties (e.g. \"Google Spain SL and Google Inc. v Agencia Española de Protección de Datos (AEPD) and Mario Costeja González.\"), or the court/AG descriptor when the case names none, with the rest in formation, referring_court, subject_matter, and case_reference, when the parser places the title whole; otherwise the raw \"#\"-delimited English title, or the served language's raw title when there is no English one. Absent for some older works and judgments."
},
"notice": {
"type": "string",
"description": "How to retrieve the remaining document content; when select.annexes asked for \"ANNEX\" on an act whose annexes are numbered, which numbers select one; when work_uri names an expression or manifestation, the work served in its place; when a work_uri carries several CELEX numbers, how many it carries and which one was served; and, when no consolidated version is in effect yet, that the consolidated text served does not apply yet, or that resolve \"current_consolidated\" served the base act."
},
"content": {
"type": "string",
"description": "Body content of the act in the requested format and language. In \"paged\" mode this is the requested window; in \"full\" mode it starts at zero; under select it is the matched sections joined in document order, each source character once — a section inside another selected section (an article in a selected chapter) is carried inside the enclosing one. Every one is capped at 100000 characters. Omitted in \"metadata_only\" mode, when the window is empty, or when content is unavailable."
},
"outline": {
"type": "array",
"items": {
"type": "object",
"required": [
"kind",
"number",
"label",
"offset"
],
"properties": {
"kind": {
"type": "string",
"description": "Structural unit kind: \"chapter\", \"section\", \"article\", \"annex\", or \"recital\" in an act; \"heading\" or \"operative_part\" in case law."
},
"label": {
"type": "string",
"description": "Human label in English whatever the language and format, e.g. \"Article 17\", \"CHAPTER IV\", \"Recitals 1–173\" — the form selection.matched reports; only an xml article with no number to read keeps its own heading text. A case-law heading keeps its text as served (e.g. \"Legal context\", \"Sur les dépens\"); the operative part is \"Operative part\"."
},
"title": {
"type": "string",
"description": "Descriptive title where the act supplies one."
},
"number": {
"type": "string",
"description": "Numbering token, the same in every language (e.g. \"17\", \"6A\", \"IV\" — Roman numerals in Latin letters, French \"premier\" as \"1\"); empty for a lone unnumbered annex. A recital entry covering a run reads as a range, first–last (e.g. \"1–173\"), unless include_recitals is true. A case-law heading is numbered by its 1-based position, the number select.headings takes; empty for the operative part."
},
"offset": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Character offset of the heading in the full body of the requested format — pass as offset in a paged call to read from here."
}
},
"description": "One detected heading, addressable by its character offset into the body.",
"additionalProperties": false
},
"description": "Structural outline of the act. Present only when outline is true; an empty array means no structure was detected."
},
"has_more": {
"type": "boolean",
"description": "True when body content exists beyond the returned contiguous window. Continue in \"paged\" mode with offset = content_offset + content_chars_returned until false. Always false in \"metadata_only\" mode, and always false for outline and select responses, where that recipe cannot resume across disjoint slices — a cut selection is disclosed through the truncated enrichment instead."
},
"in_force": {
"type": "boolean",
"description": "Whether the act is currently in force — for a consolidated text, whether its base act is. When false, repealed_by, entry_into_force, and end_of_validity give the reason where CELLAR records one: an explicit repeal, an entry into force still ahead, or an end of validity — past for an expired act, possibly still ahead for one not yet in force. Some acts not in force carry none of them."
},
"language": {
"type": "string",
"description": "Language code of the returned content."
},
"subjects": {
"type": "array",
"items": {
"type": "string",
"description": "English subject label, e.g. \"Protection of personal data\"."
},
"description": "Case law: subjects of CELLAR's case-law subject classification, as English labels, sorted; what the subject filter of eurlex_get_cases matches. A controlled vocabulary, unlike the title's subject_matter keywords. Absent for legislation, and for case law with none recorded."
},
"work_uri": {
"type": "string",
"description": "CELLAR work URI."
},
"countries": {
"type": "array",
"items": {
"type": "string",
"description": "ISO 3166-1 alpha-3 country code, e.g. \"BGR\"."
},
"description": "Case law: countries CELLAR records the case as originating in, as ISO 3166-1 alpha-3 codes, sorted — the referring court's state on a preliminary reference, the defendant state on an action for failure to fulfil obligations, the applicant's state on a direct action; the values the member_state filter of eurlex_get_cases takes. Absent for legislation, and for case law with none recorded, as on Civil Service Tribunal staff cases."
},
"formation": {
"type": "string",
"description": "Case law: the formation that decided, from the title's leading segment, verbatim (e.g. \"Grand Chamber\"), or \"President\", \"Vice-President\", or \"President of the Second Chamber\" for an order issued by that office. Absent when the title names none."
},
"selection": {
"type": "object",
"required": [
"requested",
"matched",
"missed"
],
"properties": {
"missed": {
"type": "array",
"items": {
"type": "string"
},
"description": "Requested section descriptors that could not be located."
},
"matched": {
"type": "array",
"items": {
"type": "string"
},
"description": "Labels of the sections located in the body, in document order, as in the outline — in English whatever the language and format, except a case-law heading, which keeps its text as served."
},
"requested": {
"type": "array",
"items": {
"type": "string"
},
"description": "Section descriptors requested, in English whatever the language, e.g. [\"Article 17\", \"CHAPTER IV\"], or [\"Heading 2\", \"Operative part\"] for case law."
}
},
"description": "Outcome of a structural selection. Present only when select was used; content holds the matched sections joined in document order, a nested section's text once inside its enclosing section, capped at 100000 characters. When the cap cuts the join, a trailing matched section may be partly or wholly absent from content — read selected_sections for each one's own address.",
"additionalProperties": false
},
"truncated": {
"type": "boolean",
"description": "True when the returned body window was capped."
},
"procedures": {
"type": "array",
"items": {
"type": "object",
"required": [
"reference"
],
"properties": {
"status": {
"enum": [
"adopted",
"withdrawn",
"pending",
"not_adopted"
],
"type": "string",
"description": "Where the procedure stands, from the flag CELLAR sets on it: \"adopted\", \"withdrawn\" (the proposal was withdrawn), \"pending\" (no outcome yet), or \"not_adopted\". Absent when CELLAR sets none, or more than one (some older procedures are flagged both adopted and withdrawn); an absent status is not \"pending\"."
},
"reference": {
"type": "string",
"description": "Procedure reference: year, number, and procedure type, e.g. \"2021/0106(COD)\" (COD ordinary legislative procedure, CNS consultation, NLE non-legislative), the number as CELLAR writes it (e.g. \"2011/341A(COD)\"). eurlex_lookup_celex resolves it to the act that initiated the procedure. A reference CELLAR records in another shape (e.g. \"2008/0073/\") is returned as recorded."
},
"adopted_acts": {
"type": "array",
"items": {
"type": "string",
"description": "CELEX number of an act the procedure produced."
},
"description": "CELEX numbers of the acts the procedure produced, sorted — fetch each with eurlex_get_document. Present whatever the status; absent when CELLAR links no act with a CELEX."
},
"withdrawal_date": {
"type": "string",
"description": "Date the proposal was withdrawn (YYYY-MM-DD). Present when CELLAR flags the procedure withdrawn and records the date."
}
},
"description": "One interinstitutional procedure.",
"additionalProperties": false
},
"description": "The interinstitutional (legislative) procedures the act belongs to, sorted by reference: a proposal's own procedure, or the procedure that adopted an act. A work can belong to several. Distinct from procedure_types, which classifies a court case. For a consolidated text, its base act's. Absent when the act belongs to none, as for case law and acts that predate CELLAR's procedure records."
},
"legal_basis": {
"type": "array",
"items": {
"type": "object",
"required": [
"work_uri"
],
"properties": {
"work_uri": {
"type": "string",
"description": "CELLAR work URI of the legal basis act. When celex_number is present, pass either as work_uri or celex_number to eurlex_get_document to fetch that act; a basis with no CELEX is a CELLAR reference that may not resolve to a fetchable work."
},
"celex_number": {
"type": "string",
"description": "CELEX number of the legal basis act (e.g. 12012E016 for TFEU Article 16). Absent when CELLAR records no CELEX for the work."
}
},
"description": "A legal basis act: its CELLAR work URI plus its CELEX number when recorded.",
"additionalProperties": false
},
"description": "Legal basis acts for this work — for a consolidated text, its base act's. Absent when none are recorded."
},
"limit_clamp": {
"type": "object",
"required": [
"requested",
"applied"
],
"properties": {
"applied": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit served: the per-call maximum."
},
"requested": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit the call asked for."
}
},
"description": "Present only when limit exceeded the per-call maximum: the value asked for and the value served. The response follows the applied value.",
"additionalProperties": false
},
"repealed_by": {
"type": "array",
"items": {
"type": "string",
"description": "CELEX number of a repealing act."
},
"description": "CELEX numbers of the acts that explicitly repeal this one, the relation eurlex_get_relations names repealed_by (implicit repeals are listed there as implicitly_repealed_by). Present only when in_force is false; for a consolidated text, its base act's."
},
"celex_number": {
"type": "string",
"description": "Confirmed CELEX number for the retrieved work."
},
"content_mode": {
"type": "string",
"description": "Content mode applied to this response: \"metadata_only\", \"paged\", or \"full\"."
},
"oj_reference": {
"type": "string",
"description": "Official Journal reference the act was published under, e.g. \"OJ L 119, 4.5.2016, p. 1–88\", \"OJ 13, 21.2.1962, p. 204–211\" (before 1968, no series letter), \"OJ L 42I, …\" (an issue class other than R), or for act-by-act publication \"OJ L, 2024/1689, 12.7.2024\" and \"OJ C, C/2024/2664, 29.4.2024\". Pages are the English edition's, or before 1973 the original-language edition's; an act also reprinted in a later issue cites the earliest. For a consolidated text, its base act's. Absent when CELLAR records no publication."
},
"is_superseded": {
"type": "boolean",
"description": "Whether a newer consolidated version (an unofficial reading aid merging later amendments) than the text served is in effect, so this text may lack those amendments. False when the text served is the newest consolidated version in effect, or a consolidated version dated after it that does not apply yet. Not a repeal/replacement signal — the base act remains the law and may still be in force (see in_force). Present whenever the act has a consolidated version in effect; absent otherwise."
},
"resource_type": {
"type": "string",
"description": "Human-readable document type label (e.g. \"Regulation\", \"Directive\"). Absent for some older works."
},
"base_act_celex": {
"type": "string",
"description": "CELEX of the base act a consolidated text consolidates (e.g. 32024R1689), linked through CELLAR rather than derived from the consolidated CELEX. Its authors, in-force status, legal basis, and EuroVoc subjects are reported here in place of the consolidation's own. Absent for a base act, and for a consolidated text whose base act is unlinked or carries no CELEX."
},
"case_reference": {
"type": "string",
"description": "Case law: the case reference from the title (e.g. \"Case C-131/12.\")."
},
"content_format": {
"type": "string",
"description": "Format of the returned content: \"html\", \"markdown\", or \"xml\"."
},
"content_offset": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Character offset where the returned contiguous window begins. Present in \"paged\" and \"full\" modes. Absent for outline and select responses, whose content is not a contiguous span — read selected_sections for each matched section's own offset."
},
"content_status": {
"enum": [
"not_requested",
"available",
"unavailable"
],
"type": "string",
"description": "Body resolution status: \"not_requested\" for metadata-only calls, \"available\" when a body was resolved, or \"unavailable\" after ordinary resolution attempts returned no usable body."
},
"subject_matter": {
"type": "string",
"description": "Case law: the subject-matter keyword list from the title (e.g. \"Personal data – Protection of individuals …\"). Free text, unlike subjects, CELLAR's subject classification."
},
"dates_of_effect": {
"type": "array",
"items": {
"type": "object",
"required": [
"date"
],
"properties": {
"date": {
"type": "string",
"description": "Date (YYYY-MM-DD)."
},
"type": {
"enum": [
"entry_into_force",
"application",
"partial_application",
"provisional_application",
"takes_effect",
"takes_partial_effect"
],
"type": "string",
"description": "What takes effect on that date: \"entry_into_force\", \"application\", \"partial_application\", \"provisional_application\", \"takes_effect\", or \"takes_partial_effect\". \"partial_application\" is a date from which only some of the act's provisions apply; the clause in provision says which. Absent when CELLAR records no type, or one outside these."
},
"provision": {
"type": "string",
"description": "The clause of the act that sets the date — e.g. \"Article 113(a)\", \"Sole article\", \"Annex II\", \"Point 3\" — numbered as CELLAR records it, so \"Article 93.1\" in an EU act is Article 93(1). Read it for which provisions the date covers. Absent when CELLAR names no single clause of the act: none at all, another act, an OJ reference, several provisions, or the text as a whole."
}
},
"description": "One date of effect.",
"additionalProperties": false
},
"description": "Every date of effect CELLAR records for the act, sorted by date, one entry per date, type, and provision (a date can carry several, e.g. entry into force and application), whether past or ahead and whatever in_force says. An act that applies in stages records its general date of application as application and each date from which only some provisions apply as partial_application. For a consolidated text, its base act's. Absent when none is recorded."
},
"end_of_validity": {
"type": "string",
"description": "Date (YYYY-MM-DD) the act's validity ends or ended: past for an expired act, and possibly in the future for one not yet in force (read it with entry_into_force), so on its own it does not mean the act expired. Present only when in_force is false and CELLAR records an actual date rather than its open-ended 9999-12-31; for a consolidated text, its base act's."
},
"procedure_types": {
"type": "array",
"items": {
"type": "string",
"description": "English procedure label, e.g. \"Action for annulment - successful\"."
},
"description": "Case law: the court procedure types CELLAR classifies the case under, as English labels with the outcome where recorded (e.g. \"Reference for a preliminary ruling\", \"Appeal - unfounded\"), sorted; what the procedure_type and outcome filters of eurlex_get_cases match. An appeal also lists the action appealed. Not a legislative procedure: those are in procedures. Absent for legislation, and for case law with none recorded."
},
"referring_court": {
"type": "string",
"description": "Case law: the national court that referred a preliminary ruling, from the title (e.g. \"Audiencia Nacional\"). Absent on direct actions and appeals."
},
"requested_celex": {
"type": "string",
"description": "The originally requested CELEX, echoed when resolve \"current_consolidated\" served a different consolidated version. celex_number holds the CELEX actually served. Absent when the served work is the one requested."
},
"entry_into_force": {
"type": "string",
"description": "Earliest entry-into-force date (YYYY-MM-DD) of an act not yet in force. Present only when in_force is false and that date is after today (UTC); for a consolidated text, its base act's. Every recorded date, typed, is in dates_of_effect."
},
"eurovoc_subjects": {
"type": "array",
"items": {
"type": "object",
"required": [
"concept_uri"
],
"properties": {
"label": {
"type": "string",
"description": "EuroVoc preferred label in the requested language. Absent when the concept has no label in that language."
},
"concept_uri": {
"type": "string",
"description": "EuroVoc concept URI (http://eurovoc.europa.eu/{id}), the exact value the eurovoc_concept filter of eurlex_search_documents accepts."
}
},
"description": "An EuroVoc subject: its concept URI plus its preferred label when available.",
"additionalProperties": false
},
"description": "EuroVoc subject classifications — for a consolidated text, its base act's. Absent when none are recorded."
},
"national_measure": {
"type": "object",
"properties": {
"pages": {
"type": "string",
"description": "Official journal pages, retaining leading zeroes."
},
"number": {
"type": "string",
"description": "Official journal issue number, verbatim."
},
"journal": {
"type": "string",
"description": "National official journal name supplied by CELLAR."
},
"publication_date": {
"type": "string",
"description": "Publication date in the national official journal; distinct from the document date. Absent when CELLAR records no real date — none, or the 1001-01-01 it records for an unknown one."
},
"notification_date": {
"type": "string",
"description": "Date the national measure was notified; not proof of complete transposition. Absent when CELLAR records no real date — none, or the 1001-01-01 it records for an unknown one."
}
},
"description": "National implementing measure publication citation and notification facts recorded on the served work. Missing facts are omitted; no source URL is inferred.",
"additionalProperties": false
},
"advocates_general": {
"type": "array",
"items": {
"type": "string",
"description": "Advocate General surname, as CELLAR records it."
},
"description": "Advocates General who delivered this case-law record, by surname as CELLAR records it (e.g. [\"Jääskinen\"]), sorted. A few Opinions of the Court list several. Absent for legislation and for case law with none recorded."
},
"content_available": {
"type": "boolean",
"description": "Whether body content was fetched from EUR-Lex. False in \"metadata_only\" mode (no fetch attempted) — use content_mode to distinguish \"not requested\" from \"unavailable upstream\"."
},
"content_omissions": {
"type": "object",
"required": [
"tables"
],
"properties": {
"tables": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of missing-table markers in the full source body, independent of the returned window."
}
},
"description": "Known source omissions; an available body can still omit substantive tables.",
"additionalProperties": false
},
"language_fallback": {
"type": "string",
"description": "Human-readable note explaining the fallback that occurred (e.g. \"Requested FR content unavailable; returned EN\"). Present only when a fallback happened."
},
"selected_sections": {
"type": "array",
"items": {
"type": "object",
"required": [
"label",
"offset",
"chars"
],
"properties": {
"chars": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Characters the section spans in the source body — pass as limit alongside offset to read exactly this section. A section longer than the maximum window is read by paging forward from offset instead."
},
"label": {
"type": "string",
"description": "Section label as in the outline, e.g. \"Article 17\", or a case-law heading's served text."
},
"offset": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Character offset of the section in the full body of the requested format — pass as offset in a paged call to read it."
}
},
"description": "One selected section, addressable on its own through the paging floor.",
"additionalProperties": false
},
"description": "Source address of each distinct section the selection located, in document order. Present only when select was used. A section nested inside another selected section keeps its own entry, though its text appears in content only once, inside the enclosing section. A selection is a set of slices, not a contiguous window, so these addresses — not content_offset — are how a caller navigates one; every section stays individually reachable even when the cap cut its text."
},
"author_institution": {
"type": "string",
"description": "Primary (first) author, by the English label of its CELLAR authority code: an EU institution or body (e.g. \"European Parliament\", \"Court of Justice\", \"European Union\"), a member state on a national implementing measure (e.g. \"Netherlands\"), an MEP by surname on a parliamentary question (e.g. \"VAN MIERT\"), \"Provisional data\" for a consolidated text with no linked base act, or for a national-court decision the deciding court (e.g. \"Supremo Tribunal de Justiça\"). A code with no English label shows the last segment of its code. Each label is accepted by the author_institution filter of eurlex_search_documents. For co-legislated acts, prefer author_institutions for the complete set. For a consolidated text, the base act's (see base_act_celex). Absent when not recorded, and for an AG opinion whose only recorded author is the Advocate General."
},
"consolidated_as_of": {
"type": "string",
"description": "Consolidation date of current_consolidated_celex in ISO 8601 (YYYY-MM-DD). Present whenever is_superseded is."
},
"requested_language": {
"type": "string",
"description": "Originally requested language code when English fallback changed the effective language reported in language."
},
"structure_detected": {
"type": "boolean",
"description": "Whether any structure was parsed from the body. Present when outline or select was used; false means no detectable chapter/article/annex structure, or for case law no section heading or operative part — read it via offset/limit or content_mode \"full\"."
},
"author_institutions": {
"type": "array",
"items": {
"type": "string",
"description": "Author label, as in author_institution."
},
"description": "All authors, labelled as in author_institution and listed once each, for acts adopted by more than one body (e.g. [\"European Parliament\", \"Council of the European Union\"]) or signed by several states. Advocates General appear in advocates_general instead. For a consolidated text, the base act's. Absent when none recorded."
},
"content_chars_total": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Total character length of the full document body. Present when content was fetched and available; use with content_offset to page through the entire act."
},
"procedure_languages": {
"type": "array",
"items": {
"type": "string",
"description": "Two-letter EUR-Lex language code, e.g. \"BG\"."
},
"description": "Case law: languages of the case, as the two-letter codes language takes, sorted. Absent for legislation, and for case law with none recorded, as on about half of the Court of Justice AG opinions and records dated before 1990."
},
"content_chars_returned": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Number of body characters returned in this response (equals content length). Present when a body was fetched and available."
},
"transposition_deadlines": {
"type": "array",
"items": {
"type": "string",
"description": "Deadline (YYYY-MM-DD)."
},
"description": "A directive's deadlines for transposition into national law, sorted. For a consolidated text, its base act's. Absent when none is recorded."
},
"current_consolidated_celex": {
"type": "string",
"description": "CELEX of the act's newest consolidated version in effect (e.g. 02014R0833-20260424) — fetch it with eurlex_get_document, or pass resolve \"current_consolidated\". A consolidation dated in the future is never this version. Present whenever is_superseded is."
},
"alternative_representations": {
"type": "array",
"items": {
"type": "object",
"required": [
"format",
"language",
"url"
],
"properties": {
"url": {
"type": "string",
"description": "CELLAR-advertised stream URL for this work and language."
},
"format": {
"type": "string",
"const": "pdf",
"description": "Alternative format advertised by CELLAR."
},
"language": {
"type": "string",
"description": "Language of this representation."
}
},
"description": "One explicitly advertised PDF stream.",
"additionalProperties": false
},
"description": "Verified alternative PDF stream locations; no claim that they contain every omitted table."
},
"content_unavailability_reason": {
"enum": [
"no_representation",
"upstream_failure",
"multipart_incomplete"
],
"type": "string",
"description": "Why content_status is \"unavailable\": no representation exists, the upstream request failed, or a multipart Formex body could not be assembled completely."
}
},
"additionalProperties": false
}eurlex_get_document annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}eurlex_get_relations — Get CELLAR Relationship Graph
Advertised read-onlyOpen-world
Traverse the one-hop CDM relationship graph of an EU act: what it amends or is amended by, what it repeals or is repealed by (explicit and implicit), its consolidated versions, national transposition measures (on a first page also counted per member state, naming the member states with none), its legal basis and the works adopted under it, the proposal it adopts (or, for a proposal, the act that adopted it), the CJEU rulings interpreting it (or, for a ruling, the acts it interprets), and works that cite it. Amendment, repeal, interpretation, and adoption rows carry the provisions CELLAR records each edge as targeting, and article narrows interpreted_by to the rulings on one article. Returns direct relations only, paginated per relation type and direction. Requires a CELEX number or CELLAR work URI.
eurlex_get_relations input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 10000,
"minimum": 1,
"description": "Maximum related works per relation type and direction, served up to 100 per call (default 10); a larger value (up to 10,000) is served at 100 and reported in limit_clamp. It bounds each type and direction independently, so one call over every type can return up to sixteen times this many rows. Incoming edges are newest-first. Continue at next_offset for older works; narrow relation_types or lower limit for a smaller response."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 9007199254740991,
"minimum": 0,
"description": "Pagination offset applied per relation type and direction — related works to skip (default 0). Continue at the returned next_offset, the offset plus the limit served; incoming edges are newest-first, so higher offsets reach older works. Must be below 10,000: CELLAR sorts at most 10,000 related works per type and direction, so pages stop at row 10,000."
},
"article": {
"type": "string",
"pattern": "^\\s*(?:(?:[Aa][Rr][Tt][Ii][Cc][Ll][Ee]|[Aa][Rr][Tt]\\.?)\\s*)?\\d{1,4}[A-Za-z]?\\s*$|^\\s*$",
"description": "Narrow interpreted_by to the rulings with a recorded provision in this article of the act: an article number with at most one letter (17, 6a), optionally prefixed \"Article\", \"Art.\" or \"Art\", in any case. The article matches at any depth (17 matches provisions recorded in Article 17(1)(c)), leading zeros are ignored, and a letter also matches its Latin ordinal (28c matches Article 28 quater). Rulings CELLAR records no provision for are left out. Paging, has_more, and next_offset then count matching rulings only; other relation types are unaffected. With an explicit relation_types, include interpreted_by. A blank value is the same as omitting it."
},
"work_uri": {
"type": "string",
"description": "CELLAR work resource URI to traverse (e.g. http://publications.europa.eu/resource/cellar/3e485e15-11bd-11e6-ba9a-01aa75ed71a1). Used directly as the addressed work; its CELEX identity is resolved for the national_transposition act match, which stands down when the work carries several CELEX numbers — address such a work by celex_number to name the act you mean. Provide exactly one of celex_number or work_uri."
},
"celex_number": {
"anyOf": [
{
"type": "string",
"const": ""
},
{
"type": "string",
"pattern": "^[0-9A-Z][0-9A-Z()/_-]{5,}$",
"description": "CELEX number of the work (e.g. 32016R0679). Surrounding whitespace is trimmed and the value is uppercased before validation."
}
],
"description": "CELEX number of the work to traverse (e.g. 32016R0679). Provide exactly one of celex_number or work_uri."
},
"member_states": {
"type": "array",
"items": {
"type": "string",
"description": "A member state as its ISO 3166-1 alpha-3 code (DEU, GRC, GBR for the United Kingdom) or two-letter code (DE; EL or GR for Greece; UK or GB), in any case."
},
"description": "Narrow national_transposition rows to the measures of these member states — the 27 member states plus the United Kingdom, by alpha-3 or two-letter code, in any case. Paging, has_more, and next_offset then count matching measures only; other relation types are unaffected. With an explicit relation_types, include national_transposition. An empty list is the same as omitting it."
},
"relation_types": {
"type": "array",
"items": {
"enum": [
"cites",
"amends",
"amended_by",
"repeals",
"repealed_by",
"implicitly_repeals",
"implicitly_repealed_by",
"legal_basis",
"basis_for",
"interprets",
"interpreted_by",
"consolidated_version",
"national_transposition",
"adopts",
"adopted_by"
],
"type": "string"
},
"description": "Subset of relation types to return; omit for all fifteen, equivalent to listing them explicitly. Types: cites, amends, amended_by, repeals, repealed_by, implicitly_repeals, implicitly_repealed_by, legal_basis (treaty/article this act rests on), basis_for (works naming this act among their legal bases — implementing and delegated acts, decisions, Parliament resolutions, drafts; the incoming side of legal_basis), interprets (for a ruling: the acts it interprets), interpreted_by (CJEU and General Court rulings interpreting this act; the incoming side of interprets), consolidated_version (consolidated texts of this act), national_transposition (member-state implementing measures), adopts (the works this act adopts — usually its Commission proposal, also an international agreement its concluding decision adopts or a joint-committee decision; tell them apart by CELEX), adopted_by (the act that adopted this work; the incoming side of adopts). Name only the types you need to reduce the response."
}
},
"additionalProperties": false
}eurlex_get_relations output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"work_uri",
"relations",
"total",
"offset",
"has_more",
"requested_relation_types",
"empty_relation_types"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The per-direction cap. It bounds each relation type and each direction independently, so it is not an upper bound on shown: a page spanning several types and both directions can return more relations than this number."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"offset_past_window",
"invalid_identifier_args",
"member_states_not_applicable",
"article_not_applicable",
"not_found",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `offset_past_window`: offset is 10,000 or more, past the last row CELLAR sorts for one relation type and direction. `invalid_identifier_args`: Neither celex_number nor work_uri was provided, or both were. `member_states_not_applicable`: member_states was given with a relation_types list that does not include national_transposition, the only type it filters. `article_not_applicable`: article was given with a relation_types list that does not include interpreted_by, the only type it filters. `not_found`: The CELEX number, given directly or as a resource/celex/ work URI, is not found in CELLAR — resolve the identifier with eurlex_lookup_celex first. `sparql_error`: CELLAR rejected a query this traversal sent. The same call fails the same way again. `sparql_timeout`: A query this traversal sent ran past the time budget its queries share (retryable: CELLAR's response time varies, so a later call can finish), or CELLAR refused it as too costly to run (not retryable: the same query is refused again). Neither is retried within the call. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"shown": {
"type": "number",
"description": "Number of relations returned in this page, summed across every relation type and direction — not the count for any single type or direction."
},
"total": {
"type": "number",
"description": "Number of relations returned in this page (not a corpus-wide count)."
},
"notice": {
"type": "string",
"description": "Guidance for the next call: on an empty first page, how to widen the traversal; on a first page where member_states matched no national_transposition measures, the codes it named; with article, that interpreted_by leaves out rulings CELLAR records no provision for, or on a first page with none, the article it named; on a page with more rows, the offset to continue from; on a page ending at row 10,000, the relation types and directions that reached it, each with a ready-to-run eurlex_query_sparql query listing its older works; the relation types whose provisions CELLAR did not return; and on a first page with national_transposition, that CELLAR did not return transposition_summary."
},
"offset": {
"type": "number",
"description": "Pagination offset applied to this response (per relation type and direction)."
},
"article": {
"type": "string",
"description": "The article interpreted_by rows were narrowed to, normalized from the article input: the number without a prefix or leading zeros, any letter in lower case (17, 28c). Absent when no article filter was given."
},
"has_more": {
"type": "boolean",
"description": "True when an additional valid row proves at least one requested relation type/direction has more rows. False on a retained page that ends at row 10,000, the last one CELLAR sorts; its notice names the types and directions that reached it."
},
"work_uri": {
"type": "string",
"description": "CELLAR URI of the source work (the work_uri input, or resolved from the CELEX)."
},
"relations": {
"type": "array",
"items": {
"type": "object",
"required": [
"relation_type",
"direction",
"related_work_uri"
],
"properties": {
"direction": {
"type": "string",
"description": "Direction: \"outgoing\" (this work → related) or \"incoming\" (related → this work)."
},
"provisions": {
"type": "array",
"items": {
"type": "string"
},
"description": "The provisions CELLAR records this edge as targeting, distinct and sorted. They belong to the edge's object: this act on an incoming row (the articles a ruling interprets, the provisions an amending act changes), the related work on an outgoing one. Read for amends, amended_by, repeals, repealed_by, implicitly_repeals, implicitly_repealed_by, interprets, interpreted_by, adopts, and adopted_by; absent on other types and on an edge CELLAR records no provision for, which does not mean the edge reaches the whole act. Compact codes read A article, P paragraph, L point letter or subparagraph number, PT numbered point, T indent, and BIS/TER/QUATER… the Latin ordinal of a lettered article (A17P1LC is Article 17(1)(c), A28QUATER Article 28c). Authority codes precede numbers, each {CODE|URI} token written as its CODE: AR article, PA paragraph, PO or PTA point, AN annex, ALN unnumbered paragraph, TIRE indent, CHA chapter, TXT text (AR 43 PA 4 is Article 43(4))."
},
"related_date": {
"type": "string",
"description": "Document date of the related work (YYYY-MM-DD), the date rows are ordered by within each relation type and direction. Absent when CELLAR records no real document date — none, or the 1001-01-01 it records for an undated work; such rows sort last."
},
"related_title": {
"type": "string",
"description": "The related work's English title, whole. Absent when the work has no English title — most national_transposition measures are titled only in their member state's language — with no other language substituted."
},
"relation_type": {
"type": "string",
"description": "Type of relation: cites, amends, amended_by, repeals, repealed_by, implicitly_repeals, implicitly_repealed_by, legal_basis, basis_for, interprets, interpreted_by, consolidated_version, national_transposition, adopts, adopted_by."
},
"related_work_uri": {
"type": "string",
"description": "CELLAR URI of the related work."
},
"related_celex_number": {
"type": "string",
"description": "CELEX number of the related work, if available."
},
"related_member_state": {
"type": "string",
"description": "ISO 3166-1 alpha-3 code of the member state whose national measure this is (e.g. \"CZE\"), read from the three letters after the directive number in related_celex_number. Present on national_transposition rows only. The codes are the 27 member states plus \"GBR\" (the United Kingdom)."
}
},
"description": "A single CDM relation between the source work and a related work.",
"additionalProperties": false
},
"description": "Direct CDM relations for the requested work."
},
"truncated": {
"type": "boolean",
"description": "True when an additional valid row proves at least one relation type/direction has more related works — page with offset."
},
"limit_clamp": {
"type": "object",
"required": [
"requested",
"applied"
],
"properties": {
"applied": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit served: the per-call maximum."
},
"requested": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The limit the call asked for."
}
},
"description": "Present only when limit exceeded the per-call maximum: the value asked for and the value served. The response follows the applied value.",
"additionalProperties": false
},
"next_offset": {
"type": "number",
"description": "Offset plus the limit served per relation type and direction (the applied value when limit_clamp is present). Present only when has_more is true; pass it as offset to continue."
},
"celex_number": {
"type": "string",
"description": "CELEX number of the source work whose relations were traversed — the celex_number input, or the CELEX resolved from work_uri when the addressed work carries exactly one. Absent when the addressed work carries none, carries several, or its identity was not resolved because no requested relation type needs it."
},
"member_states": {
"type": "array",
"items": {
"type": "string"
},
"description": "The member states national_transposition rows were narrowed to, as ISO 3166-1 alpha-3 codes, normalized from member_states and de-duplicated. Absent when no member_states filter was given."
},
"empty_relation_types": {
"type": "array",
"items": {
"type": "string"
},
"description": "Requested relation types that returned zero relations in THIS page. Page-scoped: a type can appear here because all its edges sit beyond the current offset/limit window, not only because the act genuinely has none of that relation — so absent-from-here does not prove absent-in-CELLAR. An empty page — a first page with no edges, or an exhausted later page — returns all requested types here."
},
"transposition_summary": {
"type": "object",
"required": [
"by_member_state",
"member_states_without_measures"
],
"properties": {
"by_member_state": {
"type": "array",
"items": {
"type": "object",
"required": [
"member_state",
"measures"
],
"properties": {
"measures": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Distinct national_transposition measures of this member state — the rows member_states: [this code] pages through."
},
"latest_date": {
"type": "string",
"description": "Newest document date (YYYY-MM-DD) among this member state's measures: the related_date of its first row under member_states: [this code]. Absent when none of them has a related_date."
},
"member_state": {
"type": "string",
"description": "ISO 3166-1 alpha-3 code of the member state (GBR for the United Kingdom), as related_member_state reads it."
}
},
"description": "One member state's national transposition measures.",
"additionalProperties": false
},
"description": "Every member state in scope with at least one measure, sorted by code, the United Kingdom (GBR) included where CELLAR records its measures."
},
"member_states_without_measures": {
"type": "array",
"items": {
"type": "string"
},
"description": "Member states in scope with no measure CELLAR records for this act, sorted: the member_states filter when given, else the 27 current member states. Empty when none is missing. A missing record is not proof that a state has not transposed the act — CELLAR lacks some notified measures — and the 27 are listed whatever date each joined the EU."
}
},
"description": "Every national_transposition measure in scope tallied per member state, from one count over all of them rather than this page's rows, so limit does not bound it and total does not count it. Present on a first page (offset 0) that traverses national_transposition when at least one member state in scope has a measure; the scope is the member_states filter when given, else every member state. Absent on later pages, for a work_uri whose work carries several CELEX numbers (address it by celex_number), and when CELLAR did not return it, which the notice then says.",
"additionalProperties": false
},
"requested_relation_types": {
"type": "array",
"items": {
"type": "string"
},
"description": "The relation types this request traversed — the explicit relation_types list, or all types when it was omitted. Diff against the types present in relations[], or read empty_relation_types, to confirm which requested types returned edges."
}
},
"additionalProperties": false
}eurlex_get_relations annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}eurlex_query_sparql — Raw CELLAR SPARQL Query
Advertised read-onlyOpen-world
Run a raw, read-only SPARQL SELECT against the CELLAR Virtuoso endpoint — an escape hatch for CDM ontology traversals the curated tools do not cover. Only SELECT is accepted; update forms and ASK/CONSTRUCT/DESCRIBE are rejected before execution, and results are capped at the server row cap (100 by default). The cdm:, skos:, and xsd: prefixes are auto-injected.
eurlex_query_sparql input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sparql_query"
],
"properties": {
"sparql_query": {
"type": "string",
"minLength": 10,
"description": "A read-only SPARQL SELECT query. Leading comments and PREFIX/BASE declarations are allowed; the cdm:, skos:, and xsd: prefixes are auto-injected. LIMIT is injected at the server row cap (100 unless the deployment configures a lower one) if absent, or capped to it; to read past the cap, add ORDER BY and repeat the query with OFFSET raised by the cap (a sorted query reaches row 10,000 at most). Key CDM predicates: cdm:resource_legal_id_celex (CELEX), cdm:work_date_document (date), cdm:work_has_resource-type (type), cdm:work_is_about_concept_eurovoc (EuroVoc subject), cdm:work_cites_work (citation). CELEX is an xsd:string literal — match it as a typed triple, ?work cdm:resource_legal_id_celex \"32016R0679\"^^xsd:string (an untyped literal matches nothing, in a triple or in FILTER(?celex = \"…\"), and a FILTER(STR(…)) comparison scans every CELEX). For text, use bif:contains with a single-quoted phrase."
},
"timeout_hint": {
"type": "integer",
"maximum": 55000,
"minimum": 1000,
"description": "Optional client-side timeout in milliseconds (1000–55000). The server default (55000 unless the deployment configures another value) applies when omitted."
}
},
"additionalProperties": false
}eurlex_query_sparql output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"bindings",
"variables",
"total"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The server-enforced result ceiling that was applied."
},
"error": {
"type": "object",
"required": [
"code",
"message"
],
"properties": {
"code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "JSON-RPC error code for this failure."
},
"data": {
"type": "object",
"properties": {
"reason": {
"type": "string",
"examples": [
"not_read_only",
"unsupported_query_form",
"sparql_error",
"sparql_timeout"
],
"description": "Machine-readable failure mode. Declared by this tool: `not_read_only`: The query is a SPARQL Update operation (INSERT, DELETE, WITH, LOAD, CLEAR, CREATE, DROP, COPY, MOVE, or ADD). `unsupported_query_form`: The query is not a SELECT: an ASK, CONSTRUCT, or DESCRIBE form, an unrecognized keyword, or no query keyword after the prologue. `sparql_error`: CELLAR rejected the query: a syntax or semantic error, a compile error, or a sorted query whose OFFSET + LIMIT passes row 10,000 (SR353, answered with its own recovery: lower OFFSET or narrow the query). The same query fails the same way again. `sparql_timeout`: The query ran past the client-side timeout (timeout_hint, default 55 s; retryable: CELLAR's response time varies, so a later run can finish, though a query slower than its timeout fails every run), or Virtuoso refused it as over its estimated-cost limit (not retryable: the same query is refused again). Neither is retried within the call, which fails inside the configured bound. Other values are possible when a failure originates below the handler."
},
"recovery": {
"type": "object",
"required": [
"hint"
],
"properties": {
"hint": {
"type": "string"
}
},
"description": "Actionable next step for the caller.",
"additionalProperties": {}
},
"retryable": {
"type": "boolean",
"description": "Whether retrying may succeed."
}
},
"additionalProperties": {}
},
"message": {
"type": "string",
"description": "Human-readable description of what went wrong."
}
},
"description": "Present when the call failed. Absent on success.",
"additionalProperties": {}
},
"shown": {
"type": "number",
"description": "Number of binding rows returned in this response."
},
"total": {
"type": "number",
"description": "Number of binding rows returned (at most the server's row cap, 100 by default)."
},
"notice": {
"type": "string",
"description": "On a truncated result: how to page past the row cap with ORDER BY and OFFSET, and the 10,000-row limit on a sorted query. On a zero-row result whose query has an untyped string literal as a triple object: how to type or language-tag it, since CELLAR stores identifiers as typed literals that an untyped one never matches."
},
"bindings": {
"type": "array",
"items": {
"type": "object",
"properties": {},
"description": "A single SPARQL result row. Each key is a SELECT variable name; each value is a SPARQL term object with \"type\" (\"uri\", \"literal\", or \"bnode\") and \"value\" (the string value), plus \"datatype\" (an IRI) on a typed literal or \"xml:lang\" (a language tag) on a language-tagged literal — the two are mutually exclusive. A variable left unbound by an OPTIONAL has no key in the row at all.",
"additionalProperties": {}
},
"description": "Raw SPARQL binding rows. To extract a value from a row: row[\"varName\"]?.value. Use the variables array to iterate in query order."
},
"truncated": {
"type": "boolean",
"description": "True when the server's row cap (the deployment's configured cap, 100 by default; cap gives the value applied) limited the rows and more may exist upstream — page on with ORDER BY in the query and OFFSET raised by the cap per call (sorted queries reach row 10,000 at most), or narrow the query with FILTERs."
},
"variables": {
"type": "array",
"items": {
"type": "string",
"description": "A SELECT variable name, in the order declared in the query."
},
"description": "Variable names from the SELECT head, in query order."
}
},
"additionalProperties": false
}eurlex_query_sparql annotations
{
"readOnlyHint": true,
"openWorldHint": true
}Prompts
1 advertised
eurlex_comparative_analysis
Frame a comparative legal analysis of a policy domain across EU and US law, driving eurlex_search_documents and eurlex_get_document for the EU side and courtlistener_search_opinions for the US counterpart.
- domain
- Policy domain for the comparison (e.g. "data privacy", "antitrust", "AI regulation", "food safety"). (required)
- focus
- Optional sub-topic or specific aspect to focus on (e.g. "enforcement mechanisms", "data subject rights", "remedies").
Resources
1 advertised
eur-lex-guide
Identifier chains, conclusion gates, and CELLAR SPARQL vocabulary for the eurlex_* tools. Use when tracing an EU act's amendments, consolidated text, repeal, or national transposition; finding CJEU rulings on an article or by member state, procedure, outcome, or subject; resolving a CELEX, ELI, ECLI, case number, or Official Journal citation; filtering by EuroVoc subject; or writing an eurlex_query_sparql query.
eur-lex-guide URI
skill://eur-lex-guide/SKILL.mdEUR-Lex document metadata — EUR-Lex document metadata
Metadata snapshot for a CELLAR work by CELEX number — human-readable document type, authors by English authority label (an EU institution or body, a member state, an MEP, or a national court; each usable as the author_institution filter of eurlex_search_documents), Advocates General of a case-law record, date, English title, in-force flag, ELI (eli), Official Journal reference (oj_reference, e.g. OJ L 119, 4.5.2016, p. 1–88), every date of effect with its type and the clause that sets it (dates_of_effect: [{ date, type?, provision? }], type one of entry_into_force, application, partial_application, provisional_application, takes_effect, takes_partial_effect; provision e.g. Article 113(a), numbered as CELLAR records it), a directive's transposition deadlines (transposition_deadlines), legal basis acts (work URI plus CELEX), EuroVoc subjects (concept URI plus English label), and the legislative procedures the act belongs to, sorted (procedures: [{ reference, status?, withdrawal_date?, adopted_acts? }], reference e.g. 2021/0106(COD), status one of adopted, withdrawn, pending, not_adopted and absent when CELLAR flags none or several, withdrawal_date when CELLAR flags the procedure withdrawn, adopted_acts the CELEX numbers the procedure produced). A consolidated text keeps its own type, date, title, and ELI, and reports its base act (base_act_celex) with that act's authors, in-force flag, OJ reference, dates of effect, transposition deadlines, legal bases, subjects, and procedures.
EUR-Lex document metadata URI template
eurlex://document/{celexNumber}EUR-Lex document relations — EUR-Lex document relations
One-hop CDM relationship summary for a CELLAR work by CELEX number: amendment and repeal chain, consolidations, national transposition measures, legal basis and the works adopted under it, the proposal it adopts (or, for a proposal, the act that adopted it), interpreting rulings (or, for a ruling, what it interprets), and citations — the newest 25 per relation type and direction. Each related work carries its CELEX, its document date, and its English title where it has them.
EUR-Lex document relations URI template
eurlex://document/{celexNumber}/relationsio.modelcontextprotocol/skills
io.modelcontextprotocol/skills URI template
skill://{+path}30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 684 ms
- 95th percentile latency
- 684 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 684 ms · metadata changed · 7 tool(s), 1 resource(s), 3 resource template(s), 1 prompt(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
Claude Code configuration
claude mcp add --transport http eur-lex-mcp-server-caseyjhand https://eur-lex.caseyjhand.com/mcpCodex
Codex configuration
codex mcp add eur-lex-mcp-server-caseyjhand --url https://eur-lex.caseyjhand.com/mcpCursor
Cursor configuration
{
"mcpServers": {
"eur-lex-mcp-server-caseyjhand": {
"url": "https://eur-lex.caseyjhand.com/mcp"
}
}
}Cline
Cline configuration
{
"mcpServers": {
"eur-lex-mcp-server-caseyjhand": {
"type": "streamableHttp",
"url": "https://eur-lex.caseyjhand.com/mcp",
"disabled": false
}
}
}VS Code
VS Code configuration
{
"servers": {
"eur-lex-mcp-server-caseyjhand": {
"type": "http",
"url": "https://eur-lex.caseyjhand.com/mcp"
}
}
}Gemini CLI
Gemini CLI configuration
gemini mcp add --transport http eur-lex-mcp-server-caseyjhand https://eur-lex.caseyjhand.com/mcpClaude Desktop
Claude Desktop configuration
https://eur-lex.caseyjhand.com/mcpWindsurf
Windsurf configuration
{
"mcpServers": {
"eur-lex-mcp-server-caseyjhand": {
"serverUrl": "https://eur-lex.caseyjhand.com/mcp"
}
}
}Let your agent find its tools
Find servers like eur-lex-mcp-server from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.