chembl-mcp-server
An MCP server that provides access to ChEMBL data, allowing agents to search for compounds by name, ID, or structure, retrieve bioactivity measurements for molecules and targets, and look up drug mechanisms and indications.
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://chembl.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
- Search compounds by name, ChEMBL ID, or SMILES structure
- Retrieve bioactivity measurements like IC50 and Ki for specific compound-target pairs
- Look up drug mechanisms of action and clinical indications
- Resolve protein or gene symbols to ChEMBL target IDs
Source and maintenance
Community listingRegistry 0.5.0
- Maintenance checked
Protocol and capabilities
- Server
- chembl-mcp-server 0.5.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 7 advertised
- Resources
- 1 advertised
- Resource templates
- 3 advertised
- Prompts
- 0 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
chembl_search_molecules — chembl-search-molecules
Advertised read-onlyOpen-world
Discovery entry point for compounds. Find by name / ChEMBL ID / InChIKey with the default search_type=name (supply query), or run a structure search with search_type exact | similarity | substructure (supply structure as a SMILES). At least one of query or structure is required, and structure is required for the three structure modes. Returns ChEMBL ID, preferred name, canonical SMILES, formula, MW, AlogP, Lipinski violations, QED, max clinical phase, and the family parent_chembl_id on every row; only search_type=similarity adds a Tanimoto similarity percent. Chain molecule_chembl_id into chembl_get_bioactivities or chembl_get_drug_info. A salt often ranks ahead of its parent and carries a small share of the family's measurements, so check parent_chembl_id before chaining. A capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.
chembl_search_molecules input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Maximum molecules to return, up to 100 — a larger value is served at 100, with a notice saying so. Defaults to the server default (25) when omitted."
},
"query": {
"type": "string",
"description": "Search text for search_type=name — a drug name, ChEMBL ID, or InChIKey, e.g. \"imatinib\" or \"CHEMBL25\"."
},
"cursor": {
"type": "string",
"description": "Opaque continuation token from a previous call's nextCursor — resumes where that page ended. Omit for the first page. Re-send the same query/structure/filters that minted it (only limit may change; it sets this page's size); redeeming it against different filters walks a different result set."
},
"structure": {
"type": "string",
"description": "SMILES string for structure search, e.g. \"CC(=O)Oc1ccccc1C(=O)O\". Required when search_type is exact/similarity/substructure."
},
"search_type": {
"enum": [
"name",
"exact",
"similarity",
"substructure"
],
"type": "string",
"default": "name",
"description": "name = text lookup (query); exact = exact structure match; similarity = Tanimoto ≥ threshold; substructure = contains the structure. All structure modes need `structure`."
},
"max_phase_min": {
"type": "integer",
"maximum": 4,
"minimum": 0,
"description": "For search_type=name, restrict to compounds at or above this max clinical phase (e.g. 4 for marketed drugs only)."
},
"similarity_threshold": {
"type": "integer",
"default": 70,
"maximum": 100,
"minimum": 40,
"description": "Minimum Tanimoto similarity percent for search_type=similarity (40–100; ChEMBL rejects below 40). Ignored for other modes."
}
},
"additionalProperties": false
}chembl_search_molecules output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"molecules",
"totalCount",
"totalCountCapped",
"truncated",
"shown",
"cap"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The limit 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_found",
"rate_limited",
"invalid_structure",
"missing_input"
],
"description": "Machine-readable failure mode. Declared by this tool: `not_found`: ChEMBL has no record for the requested identifier or structure. `rate_limited`: ChEMBL rate-limits the upstream request. `invalid_structure`: ChEMBL could not parse the SMILES of a similarity or substructure search. `missing_input`: Neither query nor structure was supplied, or a structure search_type was chosen without a structure. 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 molecules returned."
},
"notice": {
"type": "string",
"description": "Guidance when nothing matched — echoes the query and suggests how to broaden — the disclosure that a limit above the maximum was served at the maximum, and, when totalCountCapped is true, that the total is ChEMBL's search ceiling and how to narrow below it."
},
"molecules": {
"type": "array",
"items": {
"type": "object",
"required": [
"molecule_chembl_id",
"pref_name",
"canonical_smiles",
"standard_inchi_key",
"full_molformula",
"mw_freebase",
"alogp",
"num_ro5_violations",
"qed_weighted",
"max_phase",
"molecule_type",
"parent_chembl_id"
],
"properties": {
"alogp": {
"type": [
"number",
"null"
],
"description": "Calculated AlogP lipophilicity, e.g. 1.31. Null when absent."
},
"max_phase": {
"type": [
"number",
"null"
],
"description": "Max clinical phase: 4 = approved, 3–1 = clinical trial phase, 0.5 = early phase 1, −1 = clinical with the phase unknown. Null when ChEMBL records no clinical development (a preclinical or research compound). The cheap druggability signal."
},
"pref_name": {
"type": [
"string",
"null"
],
"description": "Preferred name, e.g. \"ASPIRIN\". Null for many research compounds."
},
"similarity": {
"type": [
"number",
"null"
],
"description": "Tanimoto similarity percent (0–100) to the query structure. Present only on search_type=similarity results; on every other search_type the key is absent, not null."
},
"mw_freebase": {
"type": [
"number",
"null"
],
"description": "Molecular weight of the free base in g/mol, e.g. 180.16. Null when absent."
},
"qed_weighted": {
"type": [
"number",
"null"
],
"description": "QED weighted drug-likeness score, 0–1. Null when not computed."
},
"molecule_type": {
"type": [
"string",
"null"
],
"description": "Molecule type, e.g. \"Small molecule\". Null when absent."
},
"full_molformula": {
"type": [
"string",
"null"
],
"description": "Molecular formula, e.g. \"C9H8O4\". Null when absent."
},
"canonical_smiles": {
"type": [
"string",
"null"
],
"description": "Canonical SMILES structure. Null when no structure is recorded."
},
"parent_chembl_id": {
"type": "string",
"description": "The parent of the compound's family, e.g. \"CHEMBL553\" for erlotinib hydrochloride — the compound's own ID when it is the parent or ChEMBL records no hierarchy for it. A salt's measurements are a small share of its family's: pass the parent to chembl_get_drug_info, or set include_alternate_forms on chembl_get_bioactivities, to reach the whole family."
},
"molecule_chembl_id": {
"type": "string",
"description": "ChEMBL molecule ID, e.g. \"CHEMBL25\". Pass to chembl_get_bioactivities or chembl_get_drug_info."
},
"num_ro5_violations": {
"type": [
"number",
"null"
],
"description": "Lipinski rule-of-five violation count (0–4). Null when not computed."
},
"standard_inchi_key": {
"type": [
"string",
"null"
],
"description": "Standard InChIKey — chain to the pubchem server for richer chemistry. Null when absent."
}
},
"description": "A compound matched by the search.",
"additionalProperties": false
},
"description": "Matching compounds (up to the limit)."
},
"truncated": {
"type": "boolean",
"description": "True when the result was capped at the limit."
},
"nextCursor": {
"type": "string",
"description": "Opaque token for the next page — pass it back as cursor with the same filters. Absent when this page is the last one."
},
"totalCount": {
"type": "number",
"description": "Total compounds matching before the limit was applied — a lower bound when totalCountCapped is true."
},
"totalCountCapped": {
"type": "boolean",
"description": "True when totalCount is ChEMBL's ceiling for the search — 10000 for a name search, 30000 for a substructure search: at least that many compounds match, and no page past the ceiling can be reached. Narrow the query to bring the matches under it."
}
},
"additionalProperties": false
}chembl_search_molecules annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}chembl_get_bioactivities — chembl-get-bioactivities
Advertised read-onlyOpen-world
The flagship compound↔target bioactivity bridge: measurements for a molecule (target deconvolution / selectivity), a target (lead finding), or both together (how potently one compound hits one target). Supply at least one of molecule_chembl_id (from chembl_search_molecules) or target_chembl_id (from chembl_search_targets) — supplying both narrows to that compound–target pair, supplying neither is an error. A drug's measurements are often split across its salts and other alternate forms, so molecule_chembl_id reads that one form unless include_alternate_forms widens it to the whole family under its parent (a salt's ID included), every view, page, and spill reading the same family. Filter by standard_type (IC50/Ki/EC50/…), minimum potency pchembl_value_min, assay_type, organism, and variant (wild type, or one recorded mutant such as "T315I"). Each row carries its activity_comment and data_validity_comment, its assay variant, and its source document for citation. Not every measurement has a derivable pchembl_value, so potency_view picks which side of that split you get: the default "potency_ranked" returns the measurements that have one, most potent first (ChEMBL sorts the rest first otherwise, which is why they are not merged), and "null_potency" returns exactly the measurements that have none. totalCount is the honest full match count across both views either way. Mixing measurement types (IC50 vs Ki) is a scientific error — set standard_type to compare like with like. A popular target carries tens of thousands of rows: results spill to a DataCanvas table (call chembl_dataframe_describe for its columns, then chembl_dataframe_query for honest aggregates across the staged set), while an inline preview answers the immediate question. Each view stages its own table (bioactivities / bioactivities_null_potency), so running both against one canvas_id lets a UNION ALL rebuild the full set. A canvas is minted only when a view spills; pass its canvas_id back and every later non-cursor call re-stages the table of its view with its own rows, even when they fit inline or none match, so a successful call never leaves rows from an earlier query in it, and a spill that fails or is cancelled leaves the earlier table in place. The spill is bounded by a row cap (CHEMBL_MAX_SPILL_ROWS) and a time budget (CHEMBL_SPILL_DEADLINE_MS); when either stops it short of the view, truncated is true, truncated_by names the bound, and the table is a bounded slice, not the complete view. The inline rows are always capped at limit, so compare that against totalCount before treating them as the whole answer. Spilling needs the canvas, which is on unless the server sets CANVAS_PROVIDER_TYPE=none. Whenever a call stages nothing and rows remain past this page — the canvas is off, or the view fit inline with no canvas_id — nextCursor continues the view: pass it back as cursor, with the same filters and potency_view, for the next page. A cursor page is always returned inline and never staged, canvas or not.
chembl_get_bioactivities input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Maximum rows in the inline preview or cursor page, up to 1000 — a larger value is served at 1000, with a notice saying so. Defaults to the server default (25). With the canvas enabled, a view that spills still stages in full whatever the limit; when a call stages nothing, nextCursor reaches the rows past limit."
},
"cursor": {
"type": "string",
"description": "Opaque continuation token from a previous call's nextCursor — resumes the view where that page ended. Omit for the first page. Re-send the same molecule_chembl_id/target_chembl_id, include_alternate_forms, filters, and potency_view that minted it (only limit may change; it sets this page's size); redeeming it against different filters walks a different result set. A cursor page is returned inline and never staged, even with the canvas enabled."
},
"variant": {
"type": "string",
"description": "Restrict to one assay variant of the target. \"wild_type\" keeps the measurements that record no variant. Any other value keeps those whose recorded assay_variant_mutation equals it whole, case-insensitively, with spaces beside \",\" or \"/\" ignored: a substitution (\"T315I\"), a deletion (\"F508del\"), a multi-mutant in the order ChEMBL records it (\"L858R,T790M\"; \"T790M,L858R\" matches nothing, and \"L858R\" alone matches only the single mutant), or \"UNDEFINED MUTATION\" for an unspecified mutant. Read assay_variant_mutation on unfiltered rows for the recorded strings."
},
"organism": {
"type": "string",
"description": "Restrict to a target organism, e.g. \"Homo sapiens\" (case-insensitive exact match)."
},
"canvas_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{10}$",
"description": "Optional canvas ID from a prior call to reuse the same canvas. With it, the call re-stages the selected potency_view's table with this call's rows whether they spill, fit inline, or are empty, so a second query of the SAME view REPLACES (overwrites) its prior rows once it succeeds — it does not append, and a spill that fails or is cancelled leaves them — while the other view's table is left intact, which is what lets both coexist on one canvas. Omit it and a fresh canvas is minted only if the view spills. Left untouched on a cursor page, which never stages."
},
"assay_type": {
"type": "string",
"pattern": "^\\s*(?:(?:[Bb]|[Bb][Ii][Nn][Dd][Ii][Nn][Gg]|[Ff]|[Ff][Uu][Nn][Cc][Tt][Ii][Oo][Nn][Aa][Ll]|[Aa]|[Aa][Dd][Mm][Ee]|[Aa][Dd][Mm][Ee][Tt]|[Tt]|[Tt][Oo][Xx][Ii][Cc][Ii][Tt][Yy]|[Pp]|[Pp][Hh][Yy][Ss][Ii][Cc][Oo][Cc][Hh][Ee][Mm][Ii][Cc][Aa][Ll]|[Uu]|[Uu][Nn][Aa][Ss][Ss][Ii][Gg][Nn][Ee][Dd]|[Uu][Nn][Cc][Ll][Aa][Ss][Ss][Ii][Ff][Ii][Ee][Dd])\\s*)?$",
"description": "Restrict to an assay type code: \"B\" (binding), \"F\" (functional), \"A\" (ADMET), \"T\" (toxicity), \"P\" (physicochemical), \"U\" (unassigned)."
},
"potency_view": {
"enum": [
"potency_ranked",
"null_potency"
],
"type": "string",
"default": "potency_ranked",
"description": "Which side of the pchembl_value presence split to retrieve. \"potency_ranked\" (default) returns the measurements that have a derivable pchembl_value, most potent first. \"null_potency\" returns exactly the measurements that have none — the rows the ranked view excludes, otherwise unreachable. The two partition the match set and stage to separate canvas tables."
},
"standard_type": {
"type": "string",
"description": "Restrict to one measurement type, e.g. \"IC50\", \"Ki\", \"EC50\". Matched exactly, case included — ChEMBL records distinct types that differ only by case, such as \"Kd\" and \"KD\". Set this to compare potencies validly."
},
"target_chembl_id": {
"type": "string",
"pattern": "^\\s*(?:[Cc][Hh][Ee][Mm][Bb][Ll]\\d+\\s*)?$",
"description": "ChEMBL target ID (from chembl_search_targets), e.g. \"CHEMBL203\". Supply this, molecule_chembl_id, or both — both narrows to that compound–target pair."
},
"pchembl_value_min": {
"type": "number",
"description": "Minimum pchembl_value (−log10 molar potency), e.g. 7 keeps sub-100 nM activities. Only valid on the potency_ranked view — the null_potency rows have no pchembl_value to compare against."
},
"molecule_chembl_id": {
"type": "string",
"description": "ChEMBL molecule ID (from chembl_search_molecules), e.g. \"CHEMBL941\". Supply this, target_chembl_id, or both — both narrows to that compound–target pair."
},
"include_alternate_forms": {
"type": "boolean",
"default": false,
"description": "Widen molecule_chembl_id to its whole family: the parent it belongs to and every salt and other alternate form ChEMBL files under it (a drug's measurements are often split across them). A salt's ID reaches its parent's family; each row keeps the molecule_chembl_id of the form it was measured on. Requires molecule_chembl_id; combines with target_chembl_id and every filter. Defaults to false: that one form's measurements only."
}
},
"additionalProperties": false
}chembl_get_bioactivities output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"activities",
"totalCount",
"potency_view",
"spilled",
"canvas_id",
"table_name",
"staged_row_count",
"truncated",
"truncated_by",
"canvasDisabled",
"appliedFilters"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"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_found",
"rate_limited",
"missing_filter",
"not_a_chembl_id",
"alternate_forms_without_molecule",
"contradictory_potency_filter",
"canvas_capacity_exhausted"
],
"description": "Machine-readable failure mode. Declared by this tool: `not_found`: ChEMBL has no record for the requested identifier or structure. `rate_limited`: ChEMBL rate-limits the upstream request. `missing_filter`: Neither molecule_chembl_id nor target_chembl_id was supplied, so the query had nothing to scope to. `not_a_chembl_id`: molecule_chembl_id is not a ChEMBL ID like CHEMBL941, so it could match no measurement. `alternate_forms_without_molecule`: include_alternate_forms was set without molecule_chembl_id, so there was no molecule whose family to read. `contradictory_potency_filter`: pchembl_value_min was supplied alongside potency_view \"null_potency\", whose rows have no pchembl_value for the floor to compare against — the combination can only ever match zero measurements. `canvas_capacity_exhausted`: The view spilled with no canvas_id supplied, and the tenant already holds as many canvases as CANVAS_MAX_CANVASES_PER_TENANT allows, so none could be minted to stage it. 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": {}
},
"notice": {
"type": "string",
"description": "Guidance when no measurements matched (naming the spelling ChEMBL records when the standard_type sent differs from it only by case), how to SQL the staged set, or which rows of the view an inline page holds and how to continue it — led by the disclosure that a limit above the maximum was served at the maximum."
},
"spilled": {
"type": "boolean",
"description": "True when the view exceeded the inline preview and spilled to the canvas. False when it fit inline — including an inline fit re-staged on a supplied canvas_id, which table_name and staged_row_count report."
},
"canvas_id": {
"type": [
"string",
"null"
],
"description": "Canvas ID holding the staged table — pass to chembl_dataframe_describe to list its columns, then to chembl_dataframe_query to run SQL over them. Null when nothing was staged: canvas disabled, a cursor page, or an inline fit with no canvas_id supplied."
},
"truncated": {
"type": "boolean",
"description": "True when a bound stopped the page walk short of the view — the CHEMBL_MAX_SPILL_ROWS row cap or the CHEMBL_SPILL_DEADLINE_MS time budget, as truncated_by says. The staged table is then a bounded slice, NOT the complete view, so aggregates over it are a sample. Narrow the filters to bring the view under the bound."
},
"activities": {
"type": "array",
"items": {
"type": "object",
"required": [
"activity_id",
"molecule_chembl_id",
"molecule_pref_name",
"target_chembl_id",
"target_pref_name",
"target_organism",
"assay_chembl_id",
"assay_type",
"assay_description",
"standard_type",
"standard_relation",
"standard_value",
"standard_units",
"pchembl_value",
"type",
"value",
"units",
"relation",
"activity_comment",
"data_validity_comment",
"assay_variant_mutation",
"assay_variant_accession",
"document_chembl_id",
"document_year"
],
"properties": {
"type": {
"type": [
"string",
"null"
],
"description": "Original (pre-standardization) activity type string from upstream."
},
"units": {
"type": [
"string",
"null"
],
"description": "Original units string from upstream."
},
"value": {
"type": [
"string",
"null"
],
"description": "Original value string from upstream — not coerced."
},
"relation": {
"type": [
"string",
"null"
],
"description": "Original relation string from upstream."
},
"assay_type": {
"type": [
"string",
"null"
],
"description": "Assay type code: B=binding, F=functional, A=ADMET, T=toxicity, P=physicochemical, U=unclassified. Null when absent."
},
"activity_id": {
"type": "number",
"description": "ChEMBL activity row ID."
},
"document_year": {
"type": [
"number",
"null"
],
"description": "Publication year of the source document. Null when it has none, as for deposited datasets."
},
"pchembl_value": {
"type": [
"number",
"null"
],
"description": "−log10(molar potency); the rank field. Null when underivable (non-standard type, censored relation)."
},
"standard_type": {
"type": [
"string",
"null"
],
"description": "Standardized activity type, e.g. \"IC50\", \"Ki\", \"EC50\" — the comparability key. Null when absent."
},
"standard_units": {
"type": [
"string",
"null"
],
"description": "Standardized units, e.g. \"nM\". Null when absent."
},
"standard_value": {
"type": [
"number",
"null"
],
"description": "Standardized value in standard_units. Null when the measurement is missing — never 0."
},
"assay_chembl_id": {
"type": "string",
"description": "ChEMBL assay ID — pass to chembl_get_assay for provenance."
},
"target_organism": {
"type": [
"string",
"null"
],
"description": "Target organism, e.g. \"Homo sapiens\". Null when unspecified."
},
"activity_comment": {
"type": [
"string",
"null"
],
"description": "Depositor or curator comment on the result, free text such as \"Not Active\", \"Active\", or \"Inconclusive\" — often the only result when standard_value is null. Null when absent."
},
"target_chembl_id": {
"type": "string",
"description": "ChEMBL target ID the compound was measured against."
},
"target_pref_name": {
"type": [
"string",
"null"
],
"description": "Target preferred name. Null when unnamed."
},
"assay_description": {
"type": [
"string",
"null"
],
"description": "Assay description text. Null when absent."
},
"standard_relation": {
"type": [
"string",
"null"
],
"description": "Standardized relation, e.g. \"=\", \">\", \"<\". Null when absent."
},
"document_chembl_id": {
"type": [
"string",
"null"
],
"description": "ChEMBL document ID of the publication or deposited dataset the measurement comes from — cite it. Null when absent."
},
"molecule_chembl_id": {
"type": "string",
"description": "ChEMBL molecule ID of the measured compound."
},
"molecule_pref_name": {
"type": [
"string",
"null"
],
"description": "Compound preferred name. Null for many research compounds."
},
"data_validity_comment": {
"type": [
"string",
"null"
],
"description": "ChEMBL data-validity annotation, e.g. \"Outside typical range\", \"Potential transcription error\", \"Non standard unit for type\", or \"Manually validated\" (a value curators confirmed). Null when unannotated."
},
"assay_variant_mutation": {
"type": [
"string",
"null"
],
"description": "Variant of the target protein the assay measured, as ChEMBL records it: a substitution (\"T315I\"), a deletion (\"F508del\"), several joined by \",\" or \"/\" (\"L858R,T790M\"), or \"UNDEFINED MUTATION\" for an unspecified mutant. Null when no variant is recorded."
},
"assay_variant_accession": {
"type": [
"string",
"null"
],
"description": "UniProt accession of the variant protein, which can differ from the target's own. Null when no variant is recorded, and for UNDEFINED MUTATION."
}
},
"description": "One bioactivity measurement linking a compound, target, and assay.",
"additionalProperties": false
},
"description": "Bioactivity rows for the selected potency_view — the inline preview, the cursor page, or the full view when it fit without spilling."
},
"nextCursor": {
"type": "string",
"description": "Opaque token for the next page of this view — pass it back as cursor with the same filters and potency_view. Minted only when nothing was staged and rows remain past this page: with the canvas disabled, on a cursor page, or when the view fit inline with no canvas_id supplied. Absent on the last page and whenever the call staged a table (a spill, or an inline fit re-staged on a supplied canvas_id)."
},
"table_name": {
"type": [
"string",
"null"
],
"description": "Canvas table name holding the staged rowset, and the FROM target for chembl_dataframe_query SQL — \"bioactivities\" for potency_ranked, \"bioactivities_null_potency\" for null_potency. Null when nothing was staged."
},
"totalCount": {
"type": "number",
"description": "Total matching measurements upstream — the honest full count spanning BOTH potency views, before any preview cap. The staged/preview rows are the selected view of this."
},
"potency_view": {
"enum": [
"potency_ranked",
"null_potency"
],
"type": "string",
"description": "Which view these rows came from: \"potency_ranked\" = measurements with a derivable pchembl_value; \"null_potency\" = measurements with none. Re-call with the other value to reach the rest of totalCount."
},
"truncated_by": {
"anyOf": [
{
"enum": [
"row_cap",
"time_budget"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "The bound that cut the staged table short when truncated is true: \"row_cap\" — the CHEMBL_MAX_SPILL_ROWS cap; \"time_budget\" — the CHEMBL_SPILL_DEADLINE_MS budget ended the page walk, at its expiry or once what was left would not hold another page, so a re-call can stage more. Null when truncated is false."
},
"appliedFilters": {
"type": "object",
"required": [
"scope",
"standard_type",
"pchembl_value_min",
"assay_type",
"organism",
"variant"
],
"properties": {
"scope": {
"type": "string",
"description": "Which IDs scoped the query: the molecule, the target, or both when it narrowed to a compound–target pair. Under include_alternate_forms the molecule side names the family parent whose forms were read."
},
"variant": {
"type": [
"string",
"null"
],
"description": "The variant filter applied — \"wild_type\", or the variant string matched, spaces beside separators removed — or null."
},
"organism": {
"type": [
"string",
"null"
],
"description": "The organism filter applied, or null."
},
"assay_type": {
"type": [
"string",
"null"
],
"description": "The assay_type filter applied, or null."
},
"standard_type": {
"type": [
"string",
"null"
],
"description": "The standard_type filter applied, or null."
},
"pchembl_value_min": {
"type": [
"number",
"null"
],
"description": "The pchembl_value_min filter applied, or null."
}
},
"description": "Filters as the server parsed them.",
"additionalProperties": false
},
"canvasDisabled": {
"type": "boolean",
"description": "True when the server runs with the canvas off (CANVAS_PROVIDER_TYPE=none), so large sets could not spill — the inline rows are one page of the view, not the full set, and nextCursor continues it."
},
"staged_row_count": {
"type": [
"number",
"null"
],
"description": "Rows actually registered on the canvas table — 0 when a re-staged view matched nothing. Null when nothing was staged. Below the view total when truncated is true."
}
},
"additionalProperties": false
}chembl_get_bioactivities annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}chembl_search_targets — chembl-search-targets
Advertised read-onlyOpen-world
Resolve a protein/gene/UniProt accession to the ChEMBL target ID that chembl_get_bioactivities needs for the target→leads workflow. Supply at least one of accession (UniProt, e.g. P00533), gene_symbol (e.g. EGFR), or query (free-text name); filter further by organism and target_type. Returns each target with its type, organism, and component UniProt accessions + gene symbols. A UniProt accession from the uniprot/protein server is the most precise input. A capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.
chembl_search_targets input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Maximum targets to return, up to 100 — a larger value is served at 100, with a notice saying so. Defaults to the server default (25) when omitted."
},
"query": {
"type": "string",
"description": "Free-text name match against the target preferred name, e.g. \"kinase\" or \"growth factor receptor\"."
},
"cursor": {
"type": "string",
"description": "Opaque continuation token from a previous call's nextCursor — resumes where that page ended. Omit for the first page. Re-send the same accession/gene_symbol/query/filters that minted it (only limit may change; it sets this page's size); redeeming it against different filters walks a different result set."
},
"organism": {
"type": "string",
"description": "Restrict to a source organism, e.g. \"Homo sapiens\" (case-insensitive exact match)."
},
"accession": {
"type": "string",
"description": "UniProt accession of a target component, e.g. \"P00533\". The most precise resolver — from the uniprot/protein server."
},
"gene_symbol": {
"type": "string",
"description": "Gene symbol of a target component, e.g. \"EGFR\" (case-insensitive exact match)."
},
"target_type": {
"type": "string",
"description": "Restrict to a target class, e.g. \"SINGLE PROTEIN\" or \"PROTEIN COMPLEX\"."
}
},
"additionalProperties": false
}chembl_search_targets output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"targets",
"totalCount",
"truncated",
"shown",
"cap"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"cap": {
"type": "number",
"description": "The limit 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_found",
"rate_limited",
"missing_input"
],
"description": "Machine-readable failure mode. Declared by this tool: `not_found`: ChEMBL has no record for the requested identifier or structure. `rate_limited`: ChEMBL rate-limits the upstream request. `missing_input`: None of query, accession, or gene_symbol was supplied. 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 targets returned."
},
"notice": {
"type": "string",
"description": "Guidance when no target matched — echoes the filters and suggests how to broaden — and the disclosure that a limit above the maximum was served at the maximum."
},
"targets": {
"type": "array",
"items": {
"type": "object",
"required": [
"target_chembl_id",
"pref_name",
"target_type",
"organism",
"components"
],
"properties": {
"organism": {
"type": [
"string",
"null"
],
"description": "Source organism, e.g. \"Homo sapiens\". Null when unspecified."
},
"pref_name": {
"type": [
"string",
"null"
],
"description": "Preferred target name, e.g. \"Epidermal growth factor receptor\". Null when unnamed."
},
"components": {
"type": "array",
"items": {
"type": "object",
"required": [
"accession",
"gene_symbols"
],
"properties": {
"accession": {
"type": [
"string",
"null"
],
"description": "UniProt accession of the protein component, e.g. \"P00533\". Null when not a protein target."
},
"gene_symbols": {
"type": "array",
"items": {
"type": "string",
"description": "A gene symbol for this component, e.g. \"EGFR\"."
},
"description": "Gene symbols for this component, flattened from component synonyms. Empty when none are recorded."
}
},
"description": "One protein component of the target.",
"additionalProperties": false
},
"description": "Protein components with UniProt accessions and gene symbols."
},
"target_type": {
"type": [
"string",
"null"
],
"description": "Target class: \"SINGLE PROTEIN\", \"PROTEIN COMPLEX\", \"PROTEIN FAMILY\", \"CELL-LINE\", \"ORGANISM\", etc."
},
"target_chembl_id": {
"type": "string",
"description": "ChEMBL target ID, e.g. \"CHEMBL203\". Pass to chembl_get_bioactivities as target_chembl_id."
}
},
"description": "A ChEMBL target resolved from the supplied protein identifier.",
"additionalProperties": false
},
"description": "Matching targets (up to the limit)."
},
"truncated": {
"type": "boolean",
"description": "True when the result was capped at the limit."
},
"nextCursor": {
"type": "string",
"description": "Opaque token for the next page — pass it back as cursor with the same filters. Absent when this page is the last one."
},
"totalCount": {
"type": "number",
"description": "Total targets matching the filters before the limit was applied."
}
},
"additionalProperties": false
}chembl_search_targets annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}chembl_get_drug_info — chembl-get-drug-info
Advertised read-onlyOpen-world
Pharmacology for a drug (molecule): mechanism(s) of action, the molecular target(s) it acts on, action type (inhibitor / agonist / …), first-approval year, and clinical indications with the max phase reached for each. Supply molecule_chembl_id (from chembl_search_molecules) — a parent or any of its salts and other alternate forms gives the same answer: ChEMBL often records a drug's mechanisms and approved indications on a salt, so both lists cover the whole family under parent_molecule_chembl_id. Each mechanism names the form it is recorded on, and each indication is listed once per MeSH/EFO pair at the highest phase any form reached, with the forms it is recorded on, each at its own phase. Distinct from the openfda server's label/adverse-event view — this is the curated mechanism-and-indication record. A mechanism's target_chembl_id chains into chembl_get_bioactivities for compounds hitting the same target. Each list carries its own retrieval state: an empty mechanisms or indications array means the molecule has none recorded only when the matching mechanisms_status / indications_status is "complete" — "failed" means the list was not retrieved (the request ran out of time or ChEMBL answered with an error, as the matching *_failure says) and the array says nothing about the molecule, and "truncated" means the page cap fetched fewer rows than ChEMBL holds, which the matching *_total_count reports.
chembl_get_drug_info input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"molecule_chembl_id"
],
"properties": {
"molecule_chembl_id": {
"type": "string",
"minLength": 1,
"description": "ChEMBL molecule ID (from chembl_search_molecules), e.g. \"CHEMBL939\" for gefitinib, or the molecule's standard InChIKey, e.g. \"XGALLCVXEZPNRQ-UHFFFAOYSA-N\". A salt or other alternate form answers with its parent's family, the same as the parent."
}
},
"additionalProperties": false
}chembl_get_drug_info output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"molecule_chembl_id",
"parent_molecule_chembl_id",
"pref_name",
"max_phase",
"first_approval",
"mechanisms",
"mechanisms_total_count",
"mechanisms_status",
"mechanisms_failure",
"indications",
"indications_total_count",
"indications_rows_fetched",
"indications_status",
"indications_failure"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"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_found",
"rate_limited"
],
"description": "Machine-readable failure mode. Declared by this tool: `not_found`: ChEMBL has no record for the requested identifier or structure. `rate_limited`: ChEMBL rate-limits the upstream request. 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": {}
},
"notice": {
"type": "string",
"description": "Disclosure of anything the two lists do not say for themselves: a list whose upstream fetch timed out or failed (so its emptiness means nothing), a list the page cap bounded, or — only when both lists came back complete and empty — that the molecule may be a research compound rather than a drug."
},
"max_phase": {
"type": [
"number",
"null"
],
"description": "Max clinical phase across indications: 4 = approved, 3–1 = trial phase, 0.5 = early phase 1, −1 = clinical with the phase unknown. Null when ChEMBL records no clinical development."
},
"pref_name": {
"type": [
"string",
"null"
],
"description": "Preferred drug name, e.g. \"GEFITINIB\". Null when unnamed."
},
"mechanisms": {
"type": "array",
"items": {
"type": "object",
"required": [
"target_chembl_id",
"mechanism_of_action",
"action_type",
"molecule_chembl_id"
],
"properties": {
"action_type": {
"type": [
"string",
"null"
],
"description": "Action type, e.g. \"INHIBITOR\", \"AGONIST\", \"ANTAGONIST\". Null when absent."
},
"target_chembl_id": {
"type": [
"string",
"null"
],
"description": "ChEMBL target ID the mechanism acts on — chain to chembl_get_bioactivities. Null when unspecified."
},
"molecule_chembl_id": {
"type": [
"string",
"null"
],
"description": "The form of the drug the mechanism is recorded on — the parent, or one of its salts or other alternate forms. Null when ChEMBL names none."
},
"mechanism_of_action": {
"type": [
"string",
"null"
],
"description": "Mechanism of action, e.g. \"Epidermal growth factor receptor erbB1 inhibitor\". Null when absent."
}
},
"description": "One mechanism of action linked to its molecular target.",
"additionalProperties": false
},
"description": "Mechanisms of action. Empty is authoritative only when mechanisms_status is \"complete\"."
},
"indications": {
"type": "array",
"items": {
"type": "object",
"required": [
"mesh_id",
"mesh_heading",
"efo_id",
"efo_term",
"max_phase_for_ind",
"forms"
],
"properties": {
"forms": {
"type": "array",
"items": {
"type": "object",
"required": [
"molecule_chembl_id",
"max_phase_for_ind"
],
"properties": {
"max_phase_for_ind": {
"type": [
"number",
"null"
],
"description": "Max clinical phase THIS form reached for the indication — a deuterated analog can sit lower than its parent. Null when unknown."
},
"molecule_chembl_id": {
"type": "string",
"description": "A form of the drug the indication is recorded on — the parent, or one of its salts or other alternate forms."
}
},
"description": "One form the indication is recorded on, at its own phase.",
"additionalProperties": false
},
"description": "The forms of the drug the indication is recorded on, each with its own highest phase for it. Empty when ChEMBL names none."
},
"efo_id": {
"type": [
"string",
"null"
],
"description": "EFO ontology ID, e.g. \"EFO:0003060\". Null when absent."
},
"mesh_id": {
"type": [
"string",
"null"
],
"description": "MeSH descriptor ID, e.g. \"D002289\". Null when absent."
},
"efo_term": {
"type": [
"string",
"null"
],
"description": "EFO disease term, e.g. \"non-small cell lung carcinoma\". Null when absent."
},
"mesh_heading": {
"type": [
"string",
"null"
],
"description": "MeSH disease heading, e.g. \"Carcinoma, Non-Small-Cell Lung\". Null when absent."
},
"max_phase_for_ind": {
"type": [
"number",
"null"
],
"description": "Max clinical phase reached for THIS indication (4 = approved, 3–1 = trial phase, 0.5 = early phase 1, −1 = phase unknown), the highest across the forms it is recorded on. Null when unknown."
}
},
"description": "One clinical indication, listed once per MeSH/EFO pair across the drug and its alternate forms, with the highest phase reached for it and the phase each form reached.",
"additionalProperties": false
},
"description": "Clinical indications. Empty is authoritative only when indications_status is \"complete\". When \"truncated\", each indication's max_phase_for_ind and forms are lower bounds: rows past the page cap can raise a phase or add a form."
},
"first_approval": {
"type": [
"number",
"null"
],
"description": "Year of first approval, e.g. 2003. Null when unapproved or unknown."
},
"mechanisms_status": {
"enum": [
"complete",
"truncated",
"failed"
],
"type": "string",
"description": "Retrieval state of the mechanism list. \"complete\" = every row ChEMBL records for the molecule and its alternate forms is present, so an empty array is a fact about the molecule. \"truncated\" = the single-request page cap bounded the list, so the array is a prefix of mechanisms_total_count rows. \"failed\" = the list was not retrieved (the request ran out of time or ChEMBL answered with an error, as mechanisms_failure says), so the empty array is unknown data, NOT evidence that none exist — re-call chembl_get_drug_info to retry."
},
"indications_status": {
"enum": [
"complete",
"truncated",
"failed"
],
"type": "string",
"description": "Retrieval state of the indication list. \"complete\" = every row ChEMBL records for the molecule and its alternate forms is present, so an empty array is a fact about the molecule. \"truncated\" = the single-request page cap bounded the list, so the array holds the indications of the rows fetched (indications_rows_fetched, fewer than indications_total_count). \"failed\" = the list was not retrieved (the request ran out of time or ChEMBL answered with an error, as indications_failure says), so the empty array is unknown data, NOT evidence that none exist — re-call chembl_get_drug_info to retry."
},
"mechanisms_failure": {
"anyOf": [
{
"enum": [
"timeout",
"upstream_error"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "Why the mechanism list failed, when mechanisms_status is \"failed\": \"timeout\" = the request ran out of time before ChEMBL returned the list; \"upstream_error\" = ChEMBL answered with an error (a rate limit, a server error, a rejected request) or could not be reached. Null when the list did not fail."
},
"molecule_chembl_id": {
"type": "string",
"description": "The ChEMBL molecule ID queried, as the molecule's own record writes it."
},
"indications_failure": {
"anyOf": [
{
"enum": [
"timeout",
"upstream_error"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "Why the indication list failed, when indications_status is \"failed\": \"timeout\" = the request ran out of time before ChEMBL returned the list; \"upstream_error\" = ChEMBL answered with an error (a rate limit, a server error, a rejected request) or could not be reached. Null when the list did not fail."
},
"mechanisms_total_count": {
"type": [
"number",
"null"
],
"description": "Total mechanism rows ChEMBL holds for the molecule and its alternate forms. Exceeds the returned array length exactly when the status is \"truncated\". Null when the fetch failed — the count is unknown, never 0."
},
"indications_total_count": {
"type": [
"number",
"null"
],
"description": "When the status is \"complete\", the number of distinct indications — the returned array length, rows recorded on several forms counted once. When \"truncated\", the indication rows ChEMBL holds for the molecule and its alternate forms, an upper bound on the distinct indications. Null when the fetch failed — the count is unknown, never 0."
},
"indications_rows_fetched": {
"type": [
"number",
"null"
],
"description": "Indication rows fetched from ChEMBL for the molecule and its alternate forms, before rows recorded on several forms merge. When the status is \"truncated\", each row not fetched (indications_total_count minus this) can add at most one indication, so that difference bounds the indications missing. Null when the fetch failed."
},
"parent_molecule_chembl_id": {
"type": "string",
"description": "The parent of the queried molecule's family — the molecule itself when it is the parent or ChEMBL records no hierarchy for it. Both lists cover this parent and every alternate form ChEMBL files under it (salts, isotope-labelled and deuterated analogs)."
}
},
"additionalProperties": false
}chembl_get_drug_info annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}chembl_get_assay — chembl-get-assay
Advertised read-onlyOpen-world
Assay provenance behind a bioactivity row: description, type (binding / functional / ADMET / toxicity), the target it measures, organism, and ChEMBL's 1–9 confidence score (9 = direct assay on the protein target, lower = homologous or indirect). Supply assay_chembl_id from a chembl_get_bioactivities row. Call this to judge whether two measurements are comparable before ranking them together.
chembl_get_assay input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"assay_chembl_id"
],
"properties": {
"assay_chembl_id": {
"type": "string",
"pattern": "^\\s*[Cc][Hh][Ee][Mm][Bb][Ll]\\d+\\s*$",
"description": "ChEMBL assay ID from a bioactivity row's assay_chembl_id, e.g. \"CHEMBL674637\"."
}
},
"additionalProperties": false
}chembl_get_assay output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"assay_chembl_id",
"description",
"assay_type",
"assay_type_description",
"target_chembl_id",
"organism",
"confidence_score",
"confidence_description"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"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_found",
"rate_limited"
],
"description": "Machine-readable failure mode. Declared by this tool: `not_found`: ChEMBL has no record for the requested identifier or structure. `rate_limited`: ChEMBL rate-limits the upstream request. 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": {}
},
"organism": {
"type": [
"string",
"null"
],
"description": "Organism ChEMBL records for the assay itself, not its target's organism. Null when the assay records none, even when the target is a human protein."
},
"assay_type": {
"type": [
"string",
"null"
],
"description": "Assay type code: B=binding, F=functional, A=ADMET, T=toxicity, P=physicochemical, U=unclassified. Null when absent."
},
"description": {
"type": [
"string",
"null"
],
"description": "Assay description text. Null when absent."
},
"assay_chembl_id": {
"type": "string",
"description": "The ChEMBL assay ID queried."
},
"confidence_score": {
"type": [
"number",
"null"
],
"description": "ChEMBL confidence score, 1–9 (9 = direct single-protein assay; lower = homologous/indirect). Null when unscored."
},
"target_chembl_id": {
"type": [
"string",
"null"
],
"description": "ChEMBL target ID the assay measures — chain to chembl_search_targets/chembl_get_bioactivities. Null when unassigned."
},
"assay_type_description": {
"type": [
"string",
"null"
],
"description": "Human-readable assay type, e.g. \"Binding\". Null when absent."
},
"confidence_description": {
"type": [
"string",
"null"
],
"description": "Human-readable confidence description, e.g. \"Direct single protein target assigned\". Null when absent."
}
},
"additionalProperties": false
}chembl_get_assay annotations
{
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true
}chembl_dataframe_query — chembl-dataframe-query
Advertised read-only
Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities staged on a canvas — rank, group, dedupe, and aggregate across the FULL set, not the inline preview. Reference each staged table by the name chembl_get_bioactivities returned — bioactivities for its potency_ranked view, bioactivities_null_potency for null_potency; discover the staged tables and their columns with chembl_dataframe_describe. Compute honest aggregates here (e.g. SELECT molecule_chembl_id, MEDIAN(pchembl_value) AS med FROM bioactivities WHERE standard_type = 'IC50' GROUP BY 1 ORDER BY 2 DESC). Two independent bounds apply, each reported on its own field: truncated is true when the SQL result exceeded the canvas row cap, and rendered_rows says how many of the returned rows the markdown table holds once its character budget is reached (below row_count on a wide or long result). Page past either bound with SQL LIMIT/OFFSET — append e.g. LIMIT 500 OFFSET 500 and re-call; offsets reach rows beyond the canvas row cap. Unavailable when the server sets CANVAS_PROVIDER_TYPE=none.
chembl_dataframe_query input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"canvas_id",
"sql"
],
"properties": {
"sql": {
"type": "string",
"description": "A read-only SELECT against the staged tables. Reference tables by the names chembl_get_bioactivities returned."
},
"canvas_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{10}$",
"description": "Canvas ID returned by chembl_get_bioactivities — non-null whenever that call staged a table."
}
},
"additionalProperties": false
}chembl_dataframe_query output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"rows",
"row_count",
"rendered_rows",
"truncated"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"rows": {
"type": "array",
"items": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"description": "Result rows (capped at the canvas row limit). Each row is a column→value map."
},
"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": [
"canvas_disabled"
],
"description": "Machine-readable failure mode. Declared by this tool: `canvas_disabled`: The server runs with the canvas off (CANVAS_PROVIDER_TYPE=none), so no canvas exists. 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": {}
},
"row_count": {
"type": "number",
"description": "Number of rows materialized in this response."
},
"truncated": {
"type": "boolean",
"description": "True when the SQL result exceeded the canvas row cap and was truncated — the engine bounding the result set itself, not the rendering. Independent of rendered_rows; page past it with LIMIT/OFFSET."
},
"rendered_rows": {
"type": "number",
"description": "How many of those rows the markdown table in content[] holds. Below row_count when the rendered table reached its character budget — a rendering bound, INDEPENDENT of truncated: a response can be truncated:false and still render fewer rows than row_count. Re-run the same SQL with LIMIT/OFFSET to read the rows past it."
}
},
"additionalProperties": false
}chembl_dataframe_query annotations
{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}chembl_dataframe_describe — chembl-dataframe-describe
Advertised read-only
List the tables and columns staged on a canvas by chembl_get_bioactivities — inspect before calling chembl_dataframe_query to write correct SQL. Returns each table with its row count, kind (table | view), and column names + types. Unavailable when the server sets CANVAS_PROVIDER_TYPE=none.
chembl_dataframe_describe input schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"canvas_id"
],
"properties": {
"canvas_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{10}$",
"description": "Canvas ID returned by chembl_get_bioactivities — non-null whenever that call staged a table."
}
},
"additionalProperties": false
}chembl_dataframe_describe output schema
{
"type": "object",
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"tables"
]
},
{
"required": [
"error"
]
}
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"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": [
"canvas_disabled"
],
"description": "Machine-readable failure mode. Declared by this tool: `canvas_disabled`: The server runs with the canvas off (CANVAS_PROVIDER_TYPE=none), so no canvas exists. 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": {}
},
"tables": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"kind",
"row_count",
"columns"
],
"properties": {
"kind": {
"enum": [
"table",
"view"
],
"type": "string",
"description": "Whether the entry is a base table or a registered view."
},
"name": {
"type": "string",
"description": "Canvas-local table name, e.g. \"bioactivities\"."
},
"columns": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"type"
],
"properties": {
"name": {
"type": "string",
"description": "Column name, e.g. \"pchembl_value\"."
},
"type": {
"type": "string",
"description": "Column type tag, e.g. \"DOUBLE\", \"VARCHAR\", \"BIGINT\"."
}
},
"description": "One column available for SQL.",
"additionalProperties": false
},
"description": "Columns available for SQL on this table."
},
"row_count": {
"type": "number",
"description": "Number of rows in the table (materialized COUNT for views)."
}
},
"description": "One staged table or view on the canvas.",
"additionalProperties": false
},
"description": "Tables and views staged on the canvas."
}
},
"additionalProperties": false
}chembl_dataframe_describe annotations
{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}Prompts
0 advertised
Resources
1 advertised
chembl-guide
Gates and workflows for the chembl_* bioactivity tools, covering pinning a protein to its single-protein target, ranking leads without mixing mutants, salts, or repeat measurements, building a compound's target profile and selectivity with its inactive results, and checking assay provenance and approval status. Use before ranking potencies, calling a compound selective or inactive, or saying what a drug hits or is approved for from chembl_* output.
chembl-guide URI
skill://chembl-guide/SKILL.mdchembl-molecule — chembl-molecule
A molecule record by ChEMBL ID — the same shape a chembl_search_molecules row carries (ID, names, structures, properties, max clinical phase, family parent_chembl_id). Convenience injectable-context mirror of the per-molecule fetch.
chembl-molecule URI template
chembl://molecule/{chemblId}chembl-target — chembl-target
A target record by ChEMBL target ID — pref_name, type, organism, and component UniProt accessions + gene symbols. Convenience injectable-context mirror of the per-target fetch.
chembl-target URI template
chembl://target/{chemblId}io.modelcontextprotocol/skills
io.modelcontextprotocol/skills URI template
skill://{+path}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.
- 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
- 636 ms
- 95th percentile latency
- 636 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 636 ms · metadata changed · 7 tool(s), 1 resource(s), 3 resource template(s), 0 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 chembl-mcp-server-caseyjhand https://chembl.caseyjhand.com/mcpCodex
Codex configuration
codex mcp add chembl-mcp-server-caseyjhand --url https://chembl.caseyjhand.com/mcpCursor
Cursor configuration
{
"mcpServers": {
"chembl-mcp-server-caseyjhand": {
"url": "https://chembl.caseyjhand.com/mcp"
}
}
}Cline
Cline configuration
{
"mcpServers": {
"chembl-mcp-server-caseyjhand": {
"type": "streamableHttp",
"url": "https://chembl.caseyjhand.com/mcp",
"disabled": false
}
}
}VS Code
VS Code configuration
{
"servers": {
"chembl-mcp-server-caseyjhand": {
"type": "http",
"url": "https://chembl.caseyjhand.com/mcp"
}
}
}Gemini CLI
Gemini CLI configuration
gemini mcp add --transport http chembl-mcp-server-caseyjhand https://chembl.caseyjhand.com/mcpClaude Desktop
Claude Desktop configuration
https://chembl.caseyjhand.com/mcpWindsurf
Windsurf configuration
{
"mcpServers": {
"chembl-mcp-server-caseyjhand": {
"serverUrl": "https://chembl.caseyjhand.com/mcp"
}
}
}Let your agent find its tools
Find servers like chembl-mcp-server from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.