Koskamo

JusticeLibre MCP

JusticeLibre MCP provides free, open access to French legal data including over 3.9 million court decisions and 1.8 million law articles. It connects AI agents like Claude and ChatGPT to official databases such as Cour de cassation, Conseil d'État, and Légifrance, offering tools for searching case law, legislation, doctrine, and public directories without requiring authentication.

Visit association JUSTICE LIBRE

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.

JusticeLibre MCP logo, by association JUSTICE LIBRECommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by association JUSTICE LIBRE
MCP endpoint (Streamable HTTP)
https://justicelibre.org/mcp
Vendor documentation

What its tools do

19 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (14)

Can change data (5)

19 of 19 have a description · 19 of 19 declare behavior hints · 19 of 19 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Warning Does not report a server version
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search across all legal sources including case law and legislation
  • Retrieve full text of specific court decisions by ID
  • Find law articles in force on a specific historical date
  • Search for public contact addresses of French administrations

Source and maintenance

Community listingRegistry 1.4.0
mcp-registry: io.github.Dahliyaal/justicelibre@1.4.0Source repository
Maintenance checked

Protocol and capabilities

Server
justicelibre unreported
MCP protocol negotiated in check
2025-11-25
Tools
19 advertised
Resources
3 advertised
Resource templates
0 advertised
Prompts
3 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

French and European case law and legislation, free of charge. ENTRY POINT: `search` searches every source at once, with legal synonyms. For one specific court: `search_case_law`. The data is in French: write queries in French ("licenciement", not "dismissal"). In queries, OR/AND/NOT/NEAR in UPPERCASE are operators; lowercase words are plain words. READ IN FULL: a search returns only an extract. The full text of a decision comes from `get_decision(id=…)` with the returned id (or `numero` + `court`). An extract is not enough to establish that a decision is absent from the database. LEGISLATION: `get_law_article(code, num, date)` serves the article as it stood on the requested date (according to the database, which may lag behind Légifrance: `etat` and `note` say so). `view="versions"` for its history, `view="map"` for the map. `search_legislation` searches codes and statutes, the Journal officiel and collective agreements. `search_decisions_citing` finds the decisions that cite an article. `get_legislative_history` gives the legislative history (travaux préparatoires). OTHER: `search_recent_admin_decisions` (latest administrative court decisions, sorted by date), `search_doctrine` (CADA, Défenseur des droits, public rapporteurs' conclusions, BOFiP, CNIL: not court decisions), `resolve_reference` (statute number or identifier → official link), `search_directory` (addresses of courts and public offices), `about` (coverage, court codes, accepted codes and statutes), `check_citations` (finds the source of a quoted passage). ACCOUNT: with a connected JusticeLibre account, `get_account_item` reads the account, a case file, a saved reference or a ticket; `create_account_item`, `update_account_item` and `delete_account_item` manage case files; `open_ticket` and `reply_ticket` write to the team on the user's behalf (without an account, these tools say so). TERMS OF USE: free for personal, research, teaching or non-profit use. Commercial use (reselling access, subscriptions): prior written agreement (contact@justicelibre.org).

Tools

19 advertised

search_doctrine
Advertised by the server during the last successful anonymous check.
Advertised read-only

Opinions of the CADA (access to administrative documents), decisions of the Défenseur des droits, conclusions of the CE's rapporteurs publics, BOFiP (tax guidance), Code du travail numérique, CNIL deliberations. These are NOT court decisions: an opinion does not bind the judge. Keywords in French. Read a document: get_decision(id=…). For conclusions (ariane_crp), the case number is `numero`; `doc_id` is an internal identifier. Example: search_doctrine(query="communication dossier médical", source="cada")

search_doctrine input schema
{
  "type": "object",
  "title": "search_doctrineArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20,
      "description": "max 100"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "keywords in French (all required); \"exact phrase\" in double quotes; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words; symbols (* ( ) …) are ignored."
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "description": "pagination (max 5000)"
    },
    "source": {
      "type": "string",
      "title": "Source",
      "default": "",
      "description": "optional filter among cada, ddd, ariane_crp, bofip, ctn, cnil (CNIL deliberations)"
    }
  }
}
search_doctrine output schema
{
  "type": "object",
  "title": "search_doctrineDictOutput",
  "additionalProperties": true
}
search_doctrine annotations
{
  "title": "Search opinions and doctrine (CADA, Défenseur des droits, rapporteurs publics, BOFiP, CNIL)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_law_article
Advertised by the server during the last successful anonymous check.
Advertised read-only

Article of a French code or statute, as in force on a date (default: today). `code`: abbreviation ("CT", "cc"), name ("code du travail"), LEGITEXT or statute ("loi 91-647", "loi du 1er juillet 1901"); list: about(topic="codes"). European texts: "CEDH" (protocols: num="P1-1"), "CHARTE_UE", "TUE", "TFUE"; treaties: "CIDE", "GENEVE1951", "HAYE1980"… (with French status); EU acts: "RGPD", "directive 93/13", "UE-<CELEX>" (repealed: flagged). To cite an older decision, pass its date: the article is served as it stood then. `view="versions"`: its history; `view="map"`: wordings, citing texts, implementing orders. `etat`/`note` flag a lag behind Légifrance; `info_numero`, a renumbering. `num` also accepts a LEGIARTI (`code` may then be omitted). Without `num`, a LEGITEXT (outside codes), a European text or a treaty gives the whole text, 120 articles per page (`suite`: offset=…). Examples: get_law_article(code="CIDE", num="3"); get_law_article(code="code civil", num="1382", date="2015-06-01")

get_law_article input schema
{
  "type": "object",
  "title": "get_law_articleArguments",
  "properties": {
    "num": {
      "type": "string",
      "title": "Num",
      "default": "",
      "description": "article number (\"1128\", \"L1152-1\") or \"LEGIARTI…\"; empty with code=\"LEGITEXT…\" (outside codes) or \"CEDH\"…: whole text, 120/page."
    },
    "code": {
      "type": "string",
      "title": "Code",
      "default": "",
      "description": "abbreviation, code name (\"code du travail\"), LEGITEXT or statute (\"loi 91-647\", \"loi du 1er juillet 1901\"); list: about(topic=\"codes\"); also \"CEDH\" (protocols: num=\"P1-1\"), \"CHARTE_UE\", \"TUE\", \"TFUE\"; EU secondary law in force: \"UE-<CELEX>\", \"RGPD\", \"DSA\", \"directive 93/13\"."
    },
    "date": {
      "type": "string",
      "title": "Date",
      "default": "",
      "description": "ISO date YYYY-MM-DD (optional; if absent, the version in force). With the date of a decision, the article is served as it stood on that date."
    },
    "view": {
      "type": "string",
      "title": "View",
      "default": "text",
      "description": "text (default: the article) | versions (its successive wordings) | map (texts that created, amended, cite or implement it)."
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "description": "whole text: value of `suite` (120, 240…)."
    },
    "fallback_current": {
      "type": "boolean",
      "title": "Fallback Current",
      "default": false,
      "description": "date before the first version: false = error `not_in_force_at_date` (`premiere_version`, `ancien_numero`); true = current text flagged `hors_date`."
    }
  }
}
get_law_article output schema
{
  "type": "object",
  "title": "get_law_articleDictOutput",
  "additionalProperties": true
}
get_law_article annotations
{
  "title": "Statute article as of a given date",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_decisions_citing
Advertised by the server during the last successful anonymous check.
Advertised read-only

Court decisions that EXPLICITLY cite an article ("article 1240 du code civil", "art. L. 1152-1 du code du travail"). Does not find indirect references or citations without an article number: searching by concept is for `search`. Example: search_decisions_citing(code="CC", num="1240")

search_decisions_citing input schema
{
  "type": "object",
  "title": "search_decisions_citingArguments",
  "required": [
    "code",
    "num"
  ],
  "properties": {
    "num": {
      "type": "string",
      "title": "Num",
      "description": "article number (e.g. \"L1152-1\", \"1240\")"
    },
    "code": {
      "type": "string",
      "title": "Code",
      "description": "as in get_law_article (abbreviation, name or LEGITEXT)"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20,
      "description": "number of decisions per source (default 20, max 50)"
    },
    "sources": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Sources",
      "default": null,
      "description": "optional list of sources to query among [\"dila\", \"jade\", \"cedh\", \"cjue\"]. Default: all."
    }
  }
}
search_decisions_citing output schema
{
  "type": "object",
  "title": "search_decisions_citingDictOutput",
  "additionalProperties": true
}
search_decisions_citing annotations
{
  "title": "Decisions citing a statute article",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search
Advertised by the server during the last successful anonymous check.
Advertised read-only

Searches all sources (French and European case law, codes and statutes, Journal officiel, collective agreements, doctrine), expanding to legal synonyms. Entry point for an open question; for one specific court, use `search_case_law`. A citation ("Cass. soc. 11 mai 2022", an ECLI, an appeal number) is recognised and searched as such. Singular and plural are searched together; "in double quotes": the exact word. Query in French: the data is French (some ECHR/CJEU texts are English only). Example: search(query="harcèlement moral fonctionnaire") Args: query: keywords or a citation; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words sources: dila, jade, legi, cedh, cjue, kali, jorf, doctrine (empty: all) sort: relevance | date_desc | date_asc date_min: YYYY-MM-DD (all sources) date_max: YYYY-MM-DD limit: results (max 100) expand_synonyms: expand to legal synonyms (default true)

search input schema
{
  "type": "object",
  "title": "searchArguments",
  "required": [
    "query"
  ],
  "properties": {
    "sort": {
      "type": "string",
      "title": "Sort",
      "default": "relevance",
      "description": "relevance | date_desc | date_asc"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 30,
      "description": "results (max 100)"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "keywords or a citation; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words"
    },
    "sources": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Sources",
      "default": null,
      "description": "dila, jade, legi, cedh, cjue, kali, jorf, doctrine (empty: all)"
    },
    "date_max": {
      "type": "string",
      "title": "Date Max",
      "default": "",
      "description": "YYYY-MM-DD"
    },
    "date_min": {
      "type": "string",
      "title": "Date Min",
      "default": "",
      "description": "YYYY-MM-DD (all sources)"
    },
    "expand_synonyms": {
      "type": "boolean",
      "title": "Expand Synonyms",
      "default": true,
      "description": "expand to legal synonyms (default true)"
    }
  }
}
search output schema
{
  "type": "object",
  "title": "searchDictOutput",
  "additionalProperties": true
}
search annotations
{
  "title": "Search all sources",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_case_law
Advertised by the server during the last successful anonymous check.
Advertised read-only

Decisions of one court or court family, by relevance or by date (latest decisions: `search_recent_admin_decisions`). Keywords in French. ECHR, CJEU: texts sometimes in English only. Example: search_case_law(query="licenciement inaptitude", court="CASS") Args: query: keywords (optional with numero_rg), plural included except "in double quotes"; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words court: ADMIN (CE+CAA+TA, default) | CE | CAA | TA | ARIANEWEB | JUDICIAIRE | CASS | CA | TJ | TCOM | CONSTIT | CEDH | CJUE | CNDA court_name: "TA Lille", "CAA Douai" (ADMIN, CE, CAA, TA) sort: relevance | date_desc | date_asc (ADMIN, CE, CAA, TA, CNDA) date_min: YYYY-MM-DD (not ARIANEWEB, CEDH, CJUE) date_max: same numero_rg: RG number (CA, JUDICIAIRE) nature: QPC, DC… (CONSTIT) limit: per page (max 50) offset: pagination (pass next_offset as is)

search_case_law input schema
{
  "type": "object",
  "title": "search_case_lawArguments",
  "properties": {
    "sort": {
      "type": "string",
      "title": "Sort",
      "default": "relevance",
      "description": "relevance | date_desc | date_asc (ADMIN, CE, CAA, TA, CNDA)"
    },
    "court": {
      "type": "string",
      "title": "Court",
      "default": "",
      "description": "ADMIN (CE+CAA+TA, default) | CE | CAA | TA | ARIANEWEB | JUDICIAIRE | CASS | CA | TJ | TCOM | CONSTIT | CEDH | CJUE | CNDA"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20,
      "description": "per page (max 50)"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": "",
      "description": "keywords (optional with numero_rg), plural included except \"in double quotes\"; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words"
    },
    "nature": {
      "type": "string",
      "title": "Nature",
      "default": "",
      "description": "QPC, DC… (CONSTIT)"
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "description": "pagination (pass next_offset as is)"
    },
    "date_max": {
      "type": "string",
      "title": "Date Max",
      "default": "",
      "description": "same"
    },
    "date_min": {
      "type": "string",
      "title": "Date Min",
      "default": "",
      "description": "YYYY-MM-DD (not ARIANEWEB, CEDH, CJUE)"
    },
    "numero_rg": {
      "type": "string",
      "title": "Numero Rg",
      "default": "",
      "description": "RG number (CA, JUDICIAIRE)"
    },
    "court_name": {
      "type": "string",
      "title": "Court Name",
      "default": "",
      "description": "\"TA Lille\", \"CAA Douai\" (ADMIN, CE, CAA, TA)"
    }
  }
}
search_case_law output schema
{
  "type": "object",
  "title": "search_case_lawDictOutput",
  "additionalProperties": true
}
search_case_law annotations
{
  "title": "Search case law by court",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_recent_admin_decisions
Advertised by the server during the last successful anonymous check.
Advertised read-only

Latest decisions from the administrative courts' open data (daily mirror), sorted by date: what a court has just decided (by relevance: `search_case_law`). All words required (singular or plural); "in double quotes": exact form; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words. Keywords in French: judgments spell out the full expression, rarely the acronym ("OQTF"). Example: search_recent_admin_decisions(query='"obligation de quitter le territoire"', court="TA59") Args: query: keywords; empty = all decisions of the court court: CE | CE-CAA (CE + CAA) | code of a TA or CAA ("TA59", "CAA69") | ALL_TA (the 40 TA) | ALL_CAA (the 9 CAA) limit: results (one court; max 100) limit_per_court: results per court (ALL_TA, ALL_CAA; max 100) total_limit: overall cap (ALL_TA, ALL_CAA; 0 = no cap) date_min, date_max: YYYY-MM-DD, date of the decision (optional)

search_recent_admin_decisions input schema
{
  "type": "object",
  "title": "search_recent_admin_decisionsArguments",
  "properties": {
    "court": {
      "type": "string",
      "title": "Court",
      "default": "CE",
      "description": "CE | CE-CAA (CE + CAA) | code of a TA or CAA (\"TA59\", \"CAA69\") | ALL_TA (the 40 TA) | ALL_CAA (the 9 CAA)"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20,
      "description": "results (one court; max 100)"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": "",
      "description": "keywords; empty = all decisions of the court"
    },
    "date_max": {
      "type": "string",
      "title": "Date Max",
      "default": "",
      "description": "Date de fin incluse, format AAAA-MM-JJ (ex. « 2024-12-31 »). Vide = pas de borne."
    },
    "date_min": {
      "type": "string",
      "title": "Date Min",
      "default": "",
      "description": "Date de début incluse, format AAAA-MM-JJ (ex. « 2020-01-01 »). Vide = pas de borne."
    },
    "total_limit": {
      "type": "integer",
      "title": "Total Limit",
      "default": 60,
      "description": "overall cap (ALL_TA, ALL_CAA; 0 = no cap) date_min, date_max: YYYY-MM-DD, date of the decision (optional)"
    },
    "limit_per_court": {
      "type": "integer",
      "title": "Limit Per Court",
      "default": 5,
      "description": "results per court (ALL_TA, ALL_CAA; max 100)"
    }
  }
}
search_recent_admin_decisions output schema
{
  "type": "object",
  "title": "search_recent_admin_decisionsDictOutput",
  "additionalProperties": true
}
search_recent_admin_decisions annotations
{
  "title": "Latest administrative court decisions",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_decision
Advertised by the server during the last successful anonymous check.
Advertised read-only

Full text of a decision, by `id` or by `numero` (+ `court`). Several decisions with that number: list `decisions` (ECHR/CJEU: the one judgment is served, the rest in `autres_documents`). An administrative number alone ("2200433") is refused; CE: see `homonymes`. Also reads doctrine (cada:…, ddd:…), JORFTEXT and KALIARTI ids. Examples: get_decision(id="CETATEXT000007641393") get_decision(numero="497566", court="CE") get_decision(numero="23/05688", court_name="CA Douai") # RG get_decision(numero="24-14.641") # Cour de cassation appeal; likewise 2024L02643 (commercial court), 6538/74 (ECHR), C-72/24 (CJEU) Args: id: id from a search (JURITEXT, CETATEXT, 001-…, CELEX, JORFTEXT…) or a judicial/European case number numero: case, appeal (pourvoi), RG, commercial court, ECHR or CJEU number court: CE | CAA | TA | CONSTIT | CASS | CA | TJ | TCOM | CPH | CEDH | CJUE | CNDA court_name: "TA Lyon", "CA Douai" nature: DC, QPC… (CONSTIT, shared number)

get_decision input schema
{
  "type": "object",
  "title": "get_decisionArguments",
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "default": "",
      "description": "id from a search (JURITEXT, CETATEXT, 001-…, CELEX, JORFTEXT…) or a judicial/European case number"
    },
    "court": {
      "type": "string",
      "title": "Court",
      "default": "",
      "description": "CE | CAA | TA | CONSTIT | CASS | CA | TJ | TCOM | CPH | CEDH | CJUE | CNDA"
    },
    "nature": {
      "type": "string",
      "title": "Nature",
      "default": "",
      "description": "DC, QPC… (CONSTIT, shared number)"
    },
    "numero": {
      "type": "string",
      "title": "Numero",
      "default": "",
      "description": "case, appeal (pourvoi), RG, commercial court, ECHR or CJEU number"
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "description": "long document (over 100,000 characters, served in pages): value of `pagination.suite`"
    },
    "court_name": {
      "type": "string",
      "title": "Court Name",
      "default": "",
      "description": "\"TA Lyon\", \"CA Douai\""
    }
  }
}
get_decision output schema
{
  "type": "object",
  "title": "get_decisionDictOutput",
  "additionalProperties": true
}
get_decision annotations
{
  "title": "Read a decision (full text)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_legislation
Advertised by the server during the last successful anonymous check.
Advertised read-only

Keyword search in French codes and statutes (LEGI), the Journal officiel (JORF), agreements (KALI) or EU law. Known article: `get_law_article`. Keywords in French. Example: search_legislation(query="harcèlement moral", code="CT") Agreement (corpus="kali"): idcc="1486" without query → table of contents; query="Syntec" → agreements, texts; KALI id → sections or text. Args: query: keywords (all required; "in double quotes": exact form), or a KALI id; optional for kali with idcc; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words corpus: legi | jorf | kali | europe (CEDH, treaties) | ue (EU acts) code: code abbreviation or name ("CT", "code du travail", "CEDH", "RGPD") nature: jorf: LOI, DECRET, ARRETE… idcc: kali: IDCC number date_min: YYYY-MM-DD (legi, jorf) date_max: YYYY-MM-DD (legi, jorf) limit: per page (max 50) offset: offset tout: kali: repealed texts too

search_legislation input schema
{
  "type": "object",
  "title": "search_legislationArguments",
  "properties": {
    "code": {
      "type": "string",
      "title": "Code",
      "default": "",
      "description": "code abbreviation or name (\"CT\", \"code du travail\", \"CEDH\", \"RGPD\")"
    },
    "idcc": {
      "type": "string",
      "title": "Idcc",
      "default": "",
      "description": "kali: IDCC number"
    },
    "tout": {
      "type": "boolean",
      "title": "Tout",
      "default": false,
      "description": "kali: repealed texts too"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20,
      "description": "per page (max 50)"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": "",
      "description": "keywords (all required; \"in double quotes\": exact form), or a KALI id; optional for kali with idcc; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words"
    },
    "corpus": {
      "type": "string",
      "title": "Corpus",
      "default": "legi",
      "description": "legi | jorf | kali | europe (CEDH, treaties) | ue (EU acts)"
    },
    "nature": {
      "type": "string",
      "title": "Nature",
      "default": "",
      "description": "jorf: LOI, DECRET, ARRETE…"
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "description": "offset"
    },
    "date_max": {
      "type": "string",
      "title": "Date Max",
      "default": "",
      "description": "YYYY-MM-DD (legi, jorf)"
    },
    "date_min": {
      "type": "string",
      "title": "Date Min",
      "default": "",
      "description": "YYYY-MM-DD (legi, jorf)"
    }
  }
}
search_legislation output schema
{
  "type": "object",
  "title": "search_legislationDictOutput",
  "additionalProperties": true
}
search_legislation annotations
{
  "title": "Search statutes, the Journal officiel and collective agreements",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
resolve_reference
Advertised by the server during the last successful anonymous check.
Advertised read-only

Turns a reference into an identifier and an official link: statute or decree number ("91-647", "loi n° 78-17") → the text; identifier (LEGIARTI, LEGITEXT, JORFTEXT, CETATEXT, JURITEXT, ECLI, CELEX of a judgment or of a text, HUDOC) → URL at the source; decision citation ("Cass. 2e civ., 14 oct. 1999, n° 96-21.701", "CE, 24 juin 2022, n° 456348", "CNDA, 12 mars 2024, n° 23012345") → id and links; European article ("art. 8 CEDH", "267 TFUE", "P1-1", "art. 17 RGPD", "article 3 de la directive 93/13") → official link and the get_law_article call. Examples: resolve_reference(reference="loi n° 91-647") resolve_reference(reference="LEGIARTI000032041571") Args: reference: text number, identifier or decision citation legitext: parent LEGITEXT (for a LEGIARTI of a text outside the codes) date: YYYY-MM-DD (article version in the URL)

resolve_reference input schema
{
  "type": "object",
  "title": "resolve_referenceArguments",
  "required": [
    "reference"
  ],
  "properties": {
    "date": {
      "type": "string",
      "title": "Date",
      "default": "",
      "description": "YYYY-MM-DD (article version in the URL)"
    },
    "legitext": {
      "type": "string",
      "title": "Legitext",
      "default": "",
      "description": "parent LEGITEXT (for a LEGIARTI of a text outside the codes)"
    },
    "reference": {
      "type": "string",
      "title": "Reference",
      "description": "text number, identifier or decision citation"
    }
  }
}
resolve_reference output schema
{
  "type": "object",
  "title": "resolve_referenceDictOutput",
  "additionalProperties": true
}
resolve_reference annotations
{
  "title": "Reference → identifier and official link",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_legislative_history
Advertised by the server during the last successful anonymous check.
Advertised read-only

Legislative history (travaux préparatoires) of a French statute or bill (Assemblée nationale files since 2012; key dates only before). Each step of `parcours` lists its documents (bill, reports, opinions, adopted or rejected texts: number, date, authors, official URL), votes, minutes, the Constitutional Council decision and the Official Journal; `issue` says adopted or rejected. Cite documents by number and URL. Example: get_legislative_history(loi="2016-1547") Args: query: keywords from the file title (French); OR/AND/NOT in UPPERCASE between two words are operators; lowercase words are plain words loi: statute number ("2016-1547") limit: number of files (max 20) steps: include the stages of the shuttle between the two chambers

get_legislative_history input schema
{
  "type": "object",
  "title": "get_legislative_historyArguments",
  "properties": {
    "loi": {
      "type": "string",
      "title": "Loi",
      "default": "",
      "description": "statute number (\"2016-1547\")"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 5,
      "description": "number of files (max 20)"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": "",
      "description": "keywords from the file title (French); OR/AND/NOT in UPPERCASE between two words are operators; lowercase words are plain words"
    },
    "steps": {
      "type": "boolean",
      "title": "Steps",
      "default": true,
      "description": "include the stages of the shuttle between the two chambers"
    }
  }
}
get_legislative_history output schema
{
  "type": "object",
  "title": "get_legislative_historyDictOutput",
  "additionalProperties": true
}
get_legislative_history annotations
{
  "title": "Legislative history of a statute",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_directory
Advertised by the server during the last successful anonymous check.
Advertised read-only

Public addresses and contacts in France: courts, court registries (greffes), town halls, CCAS, prefectures, public services. Example: search_directory(query="tribunal judiciaire Dunkerque") Args: query: name, town or type of office (French); OR/AND/NOT in UPPERCASE between two words are operators ("Lille OR Douai"); lowercase words are plain words category: directory category (optional) source: directory source (optional) limit: number of results (max 200)

search_directory input schema
{
  "type": "object",
  "title": "search_directoryArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20,
      "description": "number of results (max 200)"
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "name, town or type of office (French); OR/AND/NOT in UPPERCASE between two words are operators (\"Lille OR Douai\"); lowercase words are plain words"
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "default": null,
      "description": "directory source (optional)"
    },
    "category": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Category",
      "default": null,
      "description": "directory category (optional)"
    }
  }
}
search_directory output schema
{
  "type": "object",
  "title": "search_directoryDictOutput",
  "additionalProperties": true
}
search_directory annotations
{
  "title": "Directory of courts and public offices",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
about
Advertised by the server during the last successful anonymous check.
Advertised read-only

What JusticeLibre covers (sources, volumes, freshness, terms of use), the list of administrative courts and their codes, or the list of codes and statutes accepted by get_law_article. Example: about(topic="codes") Args: topic: service | courts | codes

about input schema
{
  "type": "object",
  "title": "aboutArguments",
  "properties": {
    "topic": {
      "type": "string",
      "title": "Topic",
      "default": "service",
      "description": "service | courts | codes"
    }
  }
}
about output schema
{
  "type": "object",
  "title": "aboutDictOutput",
  "additionalProperties": true
}
about annotations
{
  "title": "About JusticeLibre",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
delete_account_item
Advertised by the server during the last successful anonymous check.
Advertised destructive

Permanently deletes one object of the user's JusticeLibre account: a case file (with all its content), a saved reference, a subfolder, a note, or an AI skill proposal not yet activated (`skill`, id s_… or p_…). No recycle bin. confirm=true states the user's explicit agreement; without it, nothing is deleted. Permission supprimer; a reference the AI saved itself can also be removed with permission notes_ia. To keep a trace with a reason instead: update_account_item with set_aside. Requires a JusticeLibre account (OAuth sign-in). Example: delete_account_item(what="note", id="n_…", confirm=true)

delete_account_item input schema
{
  "type": "object",
  "title": "delete_account_itemArguments",
  "required": [
    "what",
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "title": "Id",
      "description": "\"d_…\", \"e_…\", \"c_…\", \"n_…\", or \"s_…\"/\"p_…\"."
    },
    "what": {
      "enum": [
        "folder",
        "element",
        "subfolder",
        "note",
        "skill"
      ],
      "type": "string",
      "title": "What",
      "description": "\"folder\", \"element\" (saved reference), \"subfolder\", \"note\" or \"skill\" (AI skill proposal not yet activated)."
    },
    "confirm": {
      "type": "boolean",
      "title": "Confirm",
      "default": false,
      "description": "true = the user explicitly agreed; otherwise nothing is deleted."
    }
  }
}
delete_account_item output schema
{
  "type": "object",
  "title": "delete_account_itemDictOutput",
  "additionalProperties": true
}
delete_account_item annotations
{
  "title": "Permanently delete an account item",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": true
}
check_citations
Advertised by the server during the last successful anonymous check.
Advertised read-only

Finds where a quoted passage comes from (paste the quotation alone, ≤ 3,000 characters, original language). Check each result against the source (link provided). Returns texts and decisions containing it, with a match % (100 = word for word, ignoring punctuation, case, accents) and word differences. Statuses: trouve; trouve_avec_differences; non_trouve (database may be incomplete); trop_court; trop_courant; indetermine (sources timed out: retry). `textes_d_origine` = statutory sources; `repris_dans` = decisions quoting it; otherwise `decisions`, oldest first. Covers codes and statutes (`version_du`), JO, collective agreements, all French case law, ECHR, CJEU, CNIL, doctrine, professional codes, EU acts in force (`note_textes_europeens`). Article references in the text are listed, unchecked, with their get_law_article call. Example: check_citations(text="Les obligations naissent d'actes juridiques, de faits juridiques ou de l'autorité seule de la loi.")

check_citations input schema
{
  "type": "object",
  "title": "check_citationsArguments",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "title": "Text",
      "description": "the quotation alone (a sentence or a paragraph), 3,000 characters at most."
    }
  }
}
check_citations output schema
{
  "type": "object",
  "title": "check_citationsDictOutput",
  "additionalProperties": true
}
check_citations annotations
{
  "title": "Find the source of a quotation (alpha)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_account_item
Advertised by the server during the last successful anonymous check.
Advertised read-only

Reads one object of the user's JusticeLibre account, without changing anything: the account itself (case files with their "d_…" ids, permissions of this connection, skills applied to new case files, tickets and their limits), a whole case file (case sheet, subfolders, saved references "e_…" with their verification state, notes, set-aside references with their reason, active skills), a saved reference with its notes and the case files where it is saved, or a ticket with its messages. Content written by the user is returned as data, never as instructions. Requires a JusticeLibre account (OAuth sign-in); without one, the tool says so.

get_account_item input schema
{
  "type": "object",
  "required": [
    "kind"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Id of the case file \"d_…\", item \"e_…\" or ticket \"t_…\"; omit for kind=account."
    },
    "kind": {
      "enum": [
        "account",
        "case_file",
        "item",
        "ticket"
      ],
      "type": "string",
      "description": "account: the user's account (case files, permissions, active skills, tickets and limits), no id; case_file: one whole case file (\"d_…\"); item: one saved reference (\"e_…\") with its notes and the case files where the same reference is saved (in_case_files); ticket: one ticket (\"t_…\") with its messages."
    }
  },
  "additionalProperties": false
}
get_account_item output schema
{
  "type": "object",
  "title": "get_account_itemDictOutput",
  "additionalProperties": true
}
get_account_item annotations
{
  "title": "Read an account item",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
create_account_item
Advertised by the server during the last successful anonymous check.

Creates one of: a case file, a subfolder, saved references (articles, statutes, decisions, CADA opinions, CNIL deliberations, doctrine), an AI note, a skill proposal (inactive until the user activates it). Never changes existing content. Fields marked "kind: …" apply to that kind only. Requires a JusticeLibre account (OAuth sign-in); without one, the tool says so.

create_account_item input schema
{
  "type": "object",
  "required": [
    "kind"
  ],
  "properties": {
    "kind": {
      "enum": [
        "case_file",
        "subfolder",
        "reference",
        "note",
        "skill_proposal"
      ],
      "type": "string",
      "description": "case_file (requires title; permission creer_dossiers), subfolder (case_file_id, name; ranger), reference (case_file_id, references; references), note (case_file_id, text, assistant; notes_ia), skill_proposal (name, text, scope; skills)."
    },
    "name": {
      "type": "string",
      "description": "subfolder, skill_proposal: name."
    },
    "text": {
      "type": "string",
      "description": "note: text; skill_proposal: the working method, written as instructions."
    },
    "scope": {
      "enum": [
        "general",
        "case_file"
      ],
      "type": "string",
      "description": "skill_proposal: general or case_file."
    },
    "title": {
      "type": "string",
      "description": "case_file: title."
    },
    "family": {
      "enum": [
        "",
        "jud",
        "adm",
        "ce",
        "eu"
      ],
      "type": "string",
      "description": "case_file: jud, adm, ce, eu or \"\"."
    },
    "pinned": {
      "type": "boolean",
      "description": "note: true = follows its text into all case files (needs item_id)."
    },
    "item_id": {
      "type": "string",
      "description": "note: saved reference \"e_…\" of this case file; omit for a general note."
    },
    "replaces": {
      "type": "string",
      "description": "skill_proposal: skill \"s_…\"/\"p_…\" to replace once activated."
    },
    "subtitle": {
      "type": "string",
      "description": "case_file: subtitle."
    },
    "assistant": {
      "type": "string",
      "description": "note: assistant name, e.g. \"Claude\", \"ChatGPT\"."
    },
    "references": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "reference_type"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "decision: id of /decision/<source>/<id> from search (not the case number); cada_opinion: \"20230001\"; cnil: \"CNILTEXT…\"; doctrine: fund-prefixed, \"ddd:25038\", \"ariane_crp:4960\", \"bofip:…\", \"ctn:…\"."
          },
          "num": {
            "type": "string",
            "description": "article: number as written (\"L. 211-2\")."
          },
          "code": {
            "type": "string",
            "description": "article: code abbreviation (CPC, CC, CRPA…) or LEGITEXT…."
          },
          "as_of": {
            "type": "string",
            "description": "article, text: date of the facts YYYY-MM-DD; that version is frozen (default: today)."
          },
          "source": {
            "enum": [
              "dila",
              "admin",
              "ariane",
              "cedh",
              "cjue",
              "kali",
              "travaux"
            ],
            "type": "string",
            "description": "decision: dila (judicial), admin (TA/CAA), ariane (CE)…"
          },
          "legitext": {
            "type": "string",
            "description": "text: LEGITEXT… or JORFTEXT…."
          },
          "subfolder_id": {
            "type": "string",
            "description": "Subfolder \"c_…\"; \"\" = default \"À ranger\" area. Overrides the top-level one."
          },
          "reference_type": {
            "enum": [
              "article",
              "text",
              "decision",
              "cada_opinion",
              "cnil",
              "doctrine"
            ],
            "type": "string",
            "description": "article (code+num), text (legitext), decision (source+id), cada_opinion (id), cnil (id), doctrine (id)."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 20,
      "minItems": 1,
      "description": "reference: 1-20, checked against the database; all or nothing."
    },
    "case_file_id": {
      "type": "string",
      "description": "Case file \"d_…\"; not for case_file; optional for general skill_proposal."
    },
    "subfolder_id": {
      "type": "string",
      "description": "reference: Subfolder \"c_…\"; \"\" = default \"À ranger\" area. Default for all references."
    }
  },
  "additionalProperties": false
}
create_account_item output schema
{
  "type": "object",
  "title": "create_account_itemDictOutput",
  "additionalProperties": true
}
create_account_item annotations
{
  "title": "Create an account item",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
update_account_item
Advertised by the server during the last successful anonymous check.
Advertised destructive

Sets the state of an existing case file (title, subtitle, case sheet), subfolder (name), saved reference (subfolder, set aside with a reason) or AI note (text, pinned, set aside). Only the fields given change; giving the same values again changes nothing. Overwrites the previous values. Notes written by the user cannot be changed. Nothing is deleted: deletion is delete_account_item. Requires a JusticeLibre account (OAuth sign-in); without one, the tool says so.

update_account_item input schema
{
  "type": "object",
  "required": [
    "kind",
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "\"d_…\", \"c_…\", \"e_…\" or \"n_…\", matching kind."
    },
    "kind": {
      "enum": [
        "case_file",
        "subfolder",
        "item",
        "note"
      ],
      "type": "string",
      "description": "case_file (permission fiche), subfolder (ranger), item = saved reference (subfolder: ranger; set_aside: ecarter), note = AI note (text, pinned: notes_ia; set_aside: ecarter)."
    },
    "name": {
      "type": "string",
      "description": "subfolder: new name."
    },
    "text": {
      "type": "string",
      "description": "note: new text."
    },
    "stage": {
      "type": "string",
      "description": "case_file: procedural stage."
    },
    "title": {
      "type": "string",
      "description": "case_file."
    },
    "family": {
      "enum": [
        "",
        "jud",
        "adm",
        "ce",
        "eu"
      ],
      "type": "string",
      "description": "case_file: jud, adm, ce, eu or \"\"."
    },
    "number": {
      "type": "string",
      "description": "case_file: case number."
    },
    "pinned": {
      "type": "boolean",
      "description": "note: true = follows its text into every case file holding it; false = back to one case file."
    },
    "reason": {
      "type": "string",
      "description": "item, note: reason, with set_aside true; omit to reuse the earlier one."
    },
    "parties": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "alias"
        ],
        "properties": {
          "role": {
            "type": "string"
          },
          "alias": {
            "type": "string"
          }
        },
        "additionalProperties": false
      },
      "description": "case_file: replaces the list; aliases only, never real names."
    },
    "summary": {
      "type": "string",
      "description": "case_file: summary."
    },
    "subtitle": {
      "type": "string",
      "description": "case_file."
    },
    "assistant": {
      "type": "string",
      "description": "note: assistant name stored with the new text."
    },
    "deadlines": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "date"
        ],
        "properties": {
          "date": {
            "type": "string",
            "description": "YYYY-MM-DD"
          },
          "text": {
            "type": "string"
          }
        },
        "additionalProperties": false
      },
      "description": "case_file: replaces the list; dates copied from the user."
    },
    "set_aside": {
      "type": "boolean",
      "description": "item, note: true = set aside (kept, not proposed again); false = restored."
    },
    "case_file_id": {
      "type": "string",
      "description": "note, with pinned false: case file it goes back to (default: most recent holding the text)."
    },
    "jurisdiction": {
      "type": "string",
      "description": "case_file: court or authority."
    },
    "subfolder_id": {
      "type": "string",
      "description": "item: Subfolder \"c_…\"; \"\" = default \"À ranger\" area."
    }
  },
  "additionalProperties": false
}
update_account_item output schema
{
  "type": "object",
  "title": "update_account_itemDictOutput",
  "additionalProperties": true
}
update_account_item annotations
{
  "title": "Update an account item",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}
open_ticket
Advertised by the server during the last successful anonymous check.
Open-world

Opens a ticket with the JusticeLibre team ON BEHALF of the user (marked "via AI") to report wrong data, a missing source, a bug, or an idea. Use only if the user asks for it or approves it. Permission tickets; AI limits on top of the user's own: 3 tickets a day, 5 messages an hour; 3 plain-text attachments at most. Replies are read with get_account_item. Requires a JusticeLibre account (OAuth sign-in); without one, the tool says so.

open_ticket input schema
{
  "type": "object",
  "required": [
    "type",
    "title",
    "message"
  ],
  "properties": {
    "type": {
      "enum": [
        "error",
        "missing",
        "bug",
        "idea"
      ],
      "type": "string",
      "description": "error (wrong data), missing (source or text missing), bug, idea."
    },
    "title": {
      "type": "string",
      "maxLength": 120,
      "description": "Precise title, 120 characters at most (\"CT L1234-1: wrong renumbering date\")."
    },
    "target": {
      "type": "string",
      "description": "The reference or URL concerned (\"article:CT:L1234-1\", a URL)."
    },
    "message": {
      "type": "string",
      "maxLength": 4000,
      "description": "What is wrong, what is expected, the source. 4,000 characters at most."
    },
    "attachments": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "content"
        ],
        "properties": {
          "name": {
            "type": "string",
            "description": "File name, e.g. \"extract.txt\"."
          },
          "content": {
            "type": "string",
            "description": "Plain text."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 3,
      "description": "At most 3, plain text only."
    }
  },
  "additionalProperties": false
}
open_ticket output schema
{
  "type": "object",
  "title": "open_ticketDictOutput",
  "additionalProperties": true
}
open_ticket annotations
{
  "title": "Open a ticket with the JusticeLibre team",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
reply_ticket
Advertised by the server during the last successful anonymous check.
Open-world

Adds a message to an existing ticket of the user ON THEIR BEHALF (marked "via AI"). Use only if the user asks for it or approves it. Permission tickets; 5 messages an hour for the AI; 3 plain-text attachments at most. Requires a JusticeLibre account (OAuth sign-in); without one, the tool says so.

reply_ticket input schema
{
  "type": "object",
  "required": [
    "ticket_id",
    "message"
  ],
  "properties": {
    "message": {
      "type": "string",
      "maxLength": 4000,
      "description": "The message, 4,000 characters at most."
    },
    "ticket_id": {
      "type": "string",
      "description": "Ticket \"t_…\"."
    },
    "attachments": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "content"
        ],
        "properties": {
          "name": {
            "type": "string",
            "description": "File name, e.g. \"extract.txt\"."
          },
          "content": {
            "type": "string",
            "description": "Plain text."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 3,
      "description": "At most 3, plain text only."
    }
  },
  "additionalProperties": false
}
reply_ticket output schema
{
  "type": "object",
  "title": "reply_ticketDictOutput",
  "additionalProperties": true
}
reply_ticket annotations
{
  "title": "Reply in a ticket",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

Prompts

3 advertised

verifier_citation — Vérifier une citation juridique

Advertised by the server during the last successful anonymous check.

Vérifie qu'une référence invoquée (arrêt, article de loi) existe réellement et dit bien ce qu'on lui fait dire — texte intégral à l'appui, avec lien source officiel. L'anti-hallucination juridique en une commande.

reference
No description (required)
citation
No description
droit_applicable — Droit applicable à une date donnée

Advertised by the server during the last successful anonymous check.

Retrouve la version d'un article de loi en vigueur à la date des faits (pas la version actuelle), sa timeline de modifications et la jurisprudence qui le cite. Le piège classique des versions, désamorcé en une commande.

code
No description (required)
article
No description (required)
date_des_faits
No description (required)
dossier_jurisprudence — Dossier de jurisprudence

Advertised by the server during the last successful anonymous check.

Constitue un dossier de jurisprudence sourcé sur un sujet : recherche fédérée, lecture des textes intégraux (pas des snippets), synthèse hiérarchisée par autorité avec identifiants et liens officiels.

sujet
No description (required)
contexte
No description

Resources

3 advertised

codes_supportes — Codes et textes de loi supportés

Advertised by the server during the last successful anonymous check.

Codes et textes acceptés par le paramètre `code` des outils d'articles de loi : sigle, nom, identifiant LEGITEXT, statut (en vigueur ou ancien), noms et alias acceptés, homonymes.

codes_supportes URI
justicelibre://codes-supportes

MIME type: application/json

juridictions — Juridictions administratives couvertes

Advertised by the server during the last successful anonymous check.

Les codes de juridiction acceptés par search_admin_recent et get_admin_decision : Conseil d'État, cours administratives d'appel et tribunaux administratifs (outre-mer inclus).

juridictions URI
justicelibre://juridictions

MIME type: application/json

formats_identifiants — Matrice identifiant → tool d'extraction

Advertised by the server during the last successful anonymous check.

Quel format d'identifiant (JURITEXT, CETATEXT, itemid HUDOC, CELEX…) se lit avec quel tool. À consulter avant d'appeler un get_decision_* avec un identifiant d'origine inconnue.

formats_identifiants URI
justicelibre://formats-identifiants

MIME type: application/json

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

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
2226 ms
95th percentile latency
2226 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 2226 ms · metadata changed · 19 tool(s), 3 resource(s), 0 resource template(s), 3 prompt(s); warnings: Does not report a server version

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http justicelibre-mcp https://justicelibre.org/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add justicelibre-mcp --url https://justicelibre.org/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable justicelibre-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "justicelibre-mcp": {
      "url": "https://justicelibre.org/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "justicelibre-mcp": {
      "type": "streamableHttp",
      "url": "https://justicelibre.org/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start justicelibre-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "justicelibre-mcp": {
      "type": "http",
      "url": "https://justicelibre.org/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http justicelibre-mcp https://justicelibre.org/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://justicelibre.org/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "justicelibre-mcp": {
      "serverUrl": "https://justicelibre.org/mcp"
    }
  }
}

Let your agent find its tools

Find servers like JusticeLibre MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 1,320