Server definition
- Hash
- sha256:415db34b2a2512b5d438707071c53ad368f42ac6451675540154e679f3266679
- What it is
- What a remote MCP server returned when asked what it offers: 7 tools
The blob, as servednamed by its sha256
{
"instructions": "Drug-discovery data over ChEMBL (EBI) — the curated link between compounds, protein targets, and measured bioactivity (IC50/Ki/EC50), plus drug mechanisms and indications. Canonical chains: (1) a UniProt accession from the uniprot/protein server → chembl_search_targets → chembl_get_bioactivities for the most potent leads on a target, or with molecule_chembl_id supplied alongside target_chembl_id to narrow to how potently one compound hits that one target; (2) chembl_search_molecules → chembl_get_drug_info for a drug's mechanism and indications; (3) a molecule's standard_inchi_key → the pubchem server for richer chemistry, an approved drug (max_phase 4) → the openfda server for the FDA label and adverse events. Ranking trap: pchembl_value is comparable only within one standard_type — set the standard_type filter (mixing IC50 and Ki is a scientific error). Coverage trap: many measurements have no derivable pchembl_value and are absent from the default potency-ranked view — chembl_get_bioactivities returns them only under potency_view: \"null_potency\", which stages its own canvas table alongside the ranked one. A popular target carries tens of thousands of measurements; chembl_get_bioactivities spills the selected view to a DataCanvas table (call chembl_dataframe_describe for its columns, then chembl_dataframe_query to SQL them; requires CANVAS_PROVIDER_TYPE=duckdb), bounded by CHEMBL_MAX_SPILL_ROWS — read truncated: true as a bounded slice, not the complete view. Data from ChEMBL, licensed CC BY-SA 3.0 — attribute ChEMBL (https://www.ebi.ac.uk/chembl/) in downstream use.",
"tools": [
{
"description": "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. Requires CANVAS_PROVIDER_TYPE=duckdb.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"canvas_id": {
"description": "Canvas ID returned by chembl_get_bioactivities (spilled: true).",
"pattern": "^[A-Za-z0-9_-]{10}$",
"type": "string"
}
},
"required": [
"canvas_id"
],
"type": "object"
},
"name": "chembl_dataframe_describe",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"tables"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"description": "Machine-readable failure mode. Declared by this tool: `canvas_disabled`: Called while CANVAS_PROVIDER_TYPE is not duckdb, so no canvas exists. Other values are possible when a failure originates below the handler.",
"examples": [
"canvas_disabled"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"tables": {
"description": "Tables and views staged on the canvas.",
"items": {
"additionalProperties": false,
"description": "One staged table or view on the canvas.",
"properties": {
"columns": {
"description": "Columns available for SQL on this table.",
"items": {
"additionalProperties": false,
"description": "One column available for SQL.",
"properties": {
"name": {
"description": "Column name, e.g. \"pchembl_value\".",
"type": "string"
},
"type": {
"description": "Column type tag, e.g. \"DOUBLE\", \"VARCHAR\", \"BIGINT\".",
"type": "string"
}
},
"required": [
"name",
"type"
],
"type": "object"
},
"type": "array"
},
"kind": {
"description": "Whether the entry is a base table or a registered view.",
"enum": [
"table",
"view"
],
"type": "string"
},
"name": {
"description": "Canvas-local table name, e.g. \"bioactivities\".",
"type": "string"
},
"row_count": {
"description": "Number of rows in the table (materialized COUNT for views).",
"type": "number"
}
},
"required": [
"name",
"kind",
"row_count",
"columns"
],
"type": "object"
},
"type": "array"
}
},
"type": "object"
}
},
{
"description": "Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities spilled to 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. Requires CANVAS_PROVIDER_TYPE=duckdb.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"canvas_id": {
"description": "Canvas ID returned by chembl_get_bioactivities (spilled: true).",
"pattern": "^[A-Za-z0-9_-]{10}$",
"type": "string"
},
"sql": {
"description": "A read-only SELECT against the staged tables. Reference tables by the names chembl_get_bioactivities returned.",
"type": "string"
}
},
"required": [
"canvas_id",
"sql"
],
"type": "object"
},
"name": "chembl_dataframe_query",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"rows",
"row_count",
"rendered_rows",
"truncated"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"description": "Machine-readable failure mode. Declared by this tool: `canvas_disabled`: Called while CANVAS_PROVIDER_TYPE is not duckdb, so no canvas exists. Other values are possible when a failure originates below the handler.",
"examples": [
"canvas_disabled"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"rendered_rows": {
"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.",
"type": "number"
},
"row_count": {
"description": "Number of rows materialized in this response.",
"type": "number"
},
"rows": {
"description": "Result rows (capped at the canvas row limit). Each row is a column→value map.",
"items": {
"additionalProperties": {},
"propertyNames": {
"type": "string"
},
"type": "object"
},
"type": "array"
},
"truncated": {
"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.",
"type": "boolean"
}
},
"type": "object"
}
},
{
"description": "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.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"assay_chembl_id": {
"description": "ChEMBL assay ID from a bioactivity row's assay_chembl_id, e.g. \"CHEMBL674637\".",
"minLength": 1,
"type": "string"
}
},
"required": [
"assay_chembl_id"
],
"type": "object"
},
"name": "chembl_get_assay",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"assay_chembl_id",
"description",
"assay_type",
"assay_type_description",
"target_chembl_id",
"organism",
"confidence_score",
"confidence_description"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"assay_chembl_id": {
"description": "The ChEMBL assay ID queried.",
"type": "string"
},
"assay_type": {
"description": "Assay type code: B=binding, F=functional, A=ADMET, T=toxicity, P=physicochemical, U=unclassified. Null when absent.",
"type": [
"string",
"null"
]
},
"assay_type_description": {
"description": "Human-readable assay type, e.g. \"Binding\". Null when absent.",
"type": [
"string",
"null"
]
},
"confidence_description": {
"description": "Human-readable confidence description, e.g. \"Direct single protein target assigned\". Null when absent.",
"type": [
"string",
"null"
]
},
"confidence_score": {
"description": "ChEMBL confidence score, 1–9 (9 = direct single-protein assay; lower = homologous/indirect). Null when unscored.",
"type": [
"number",
"null"
]
},
"description": {
"description": "Assay description text. Null when absent.",
"type": [
"string",
"null"
]
},
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"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.",
"examples": [
"not_found",
"rate_limited"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"organism": {
"description": "Assay organism. Null when unspecified.",
"type": [
"string",
"null"
]
},
"target_chembl_id": {
"description": "ChEMBL target ID the assay measures — chain to chembl_search_targets/chembl_get_bioactivities. Null when unassigned.",
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
{
"description": "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. Filter by standard_type (IC50/Ki/EC50/…), minimum potency pchembl_value_min, assay_type, and organism. 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. The staged table is capped at CHEMBL_MAX_SPILL_ROWS; when the cap is hit, truncated is true 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 the rest requires CANVAS_PROVIDER_TYPE=duckdb; without it the inline preview is all there is.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"assay_type": {
"description": "Restrict to an assay type code: \"B\" (binding), \"F\" (functional), \"A\" (ADMET), \"T\" (toxicity).",
"type": "string"
},
"canvas_id": {
"description": "Optional canvas ID from a prior call to reuse the same canvas. Each potency_view re-stages its own table, so a second query of the SAME view REPLACES (overwrites) its prior rows — it does not append — while the other view's table is left intact, which is what lets both coexist on one canvas. Omit to mint a fresh canvas.",
"pattern": "^[A-Za-z0-9_-]{10}$",
"type": "string"
},
"limit": {
"description": "Maximum rows in the inline preview. Defaults to the server default (25). The full set still spills to the canvas.",
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"molecule_chembl_id": {
"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.",
"type": "string"
},
"organism": {
"description": "Restrict to a target organism, e.g. \"Homo sapiens\" (case-insensitive exact match).",
"type": "string"
},
"pchembl_value_min": {
"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.",
"type": "number"
},
"potency_view": {
"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.",
"enum": [
"potency_ranked",
"null_potency"
],
"type": "string"
},
"standard_type": {
"description": "Restrict to one measurement type, e.g. \"IC50\", \"Ki\", \"EC50\". Set this to compare potencies validly.",
"type": "string"
},
"target_chembl_id": {
"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.",
"type": "string"
}
},
"type": "object"
},
"name": "chembl_get_bioactivities",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"activities",
"totalCount",
"potency_view",
"spilled",
"canvas_id",
"table_name",
"staged_row_count",
"truncated",
"canvasDisabled",
"appliedFilters"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"activities": {
"description": "Bioactivity rows for the selected potency_view — the inline preview, or the full view when it fit without spilling.",
"items": {
"additionalProperties": false,
"description": "One bioactivity measurement linking a compound, target, and assay.",
"properties": {
"activity_id": {
"description": "ChEMBL activity row ID.",
"type": "number"
},
"assay_chembl_id": {
"description": "ChEMBL assay ID — pass to chembl_get_assay for provenance.",
"type": "string"
},
"assay_description": {
"description": "Assay description text. Null when absent.",
"type": [
"string",
"null"
]
},
"assay_type": {
"description": "Assay type code: B=binding, F=functional, A=ADMET, T=toxicity, P=physicochemical, U=unclassified. Null when absent.",
"type": [
"string",
"null"
]
},
"molecule_chembl_id": {
"description": "ChEMBL molecule ID of the measured compound.",
"type": "string"
},
"molecule_pref_name": {
"description": "Compound preferred name. Null for many research compounds.",
"type": [
"string",
"null"
]
},
"pchembl_value": {
"description": "−log10(molar potency); the rank field. Null when underivable (non-standard type, censored relation).",
"type": [
"number",
"null"
]
},
"relation": {
"description": "Original relation string from upstream.",
"type": [
"string",
"null"
]
},
"standard_relation": {
"description": "Standardized relation, e.g. \"=\", \">\", \"<\". Null when absent.",
"type": [
"string",
"null"
]
},
"standard_type": {
"description": "Standardized activity type, e.g. \"IC50\", \"Ki\", \"EC50\" — the comparability key. Null when absent.",
"type": [
"string",
"null"
]
},
"standard_units": {
"description": "Standardized units, e.g. \"nM\". Null when absent.",
"type": [
"string",
"null"
]
},
"standard_value": {
"description": "Standardized value in standard_units. Null when the measurement is missing — never 0.",
"type": [
"number",
"null"
]
},
"target_chembl_id": {
"description": "ChEMBL target ID the compound was measured against.",
"type": "string"
},
"target_organism": {
"description": "Target organism, e.g. \"Homo sapiens\". Null when unspecified.",
"type": [
"string",
"null"
]
},
"target_pref_name": {
"description": "Target preferred name. Null when unnamed.",
"type": [
"string",
"null"
]
},
"type": {
"description": "Original (pre-standardization) activity type string from upstream.",
"type": [
"string",
"null"
]
},
"units": {
"description": "Original units string from upstream.",
"type": [
"string",
"null"
]
},
"value": {
"description": "Original value string from upstream — not coerced.",
"type": [
"string",
"null"
]
}
},
"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"
],
"type": "object"
},
"type": "array"
},
"appliedFilters": {
"additionalProperties": false,
"description": "Filters as the server parsed them.",
"properties": {
"assay_type": {
"description": "The assay_type filter applied, or null.",
"type": [
"string",
"null"
]
},
"organism": {
"description": "The organism filter applied, or null.",
"type": [
"string",
"null"
]
},
"pchembl_value_min": {
"description": "The pchembl_value_min filter applied, or null.",
"type": [
"number",
"null"
]
},
"scope": {
"description": "Which IDs scoped the query: the molecule, the target, or both when it narrowed to a compound–target pair.",
"type": "string"
},
"standard_type": {
"description": "The standard_type filter applied, or null.",
"type": [
"string",
"null"
]
}
},
"required": [
"scope",
"standard_type",
"pchembl_value_min",
"assay_type",
"organism"
],
"type": "object"
},
"canvasDisabled": {
"description": "True when CANVAS_PROVIDER_TYPE is not duckdb, so large sets could not spill — the inline rows are a capped preview, not the full set.",
"type": "boolean"
},
"canvas_id": {
"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 canvas is disabled or nothing spilled.",
"type": [
"string",
"null"
]
},
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"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. `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. Other values are possible when a failure originates below the handler.",
"examples": [
"not_found",
"rate_limited",
"missing_filter",
"contradictory_potency_filter"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"notice": {
"description": "Guidance when no measurements matched, or how to SQL the spilled set.",
"type": "string"
},
"potency_view": {
"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.",
"enum": [
"potency_ranked",
"null_potency"
],
"type": "string"
},
"spilled": {
"description": "True when the view exceeded the preview and was staged on the canvas.",
"type": "boolean"
},
"staged_row_count": {
"description": "Rows actually registered on the canvas table. Null when nothing spilled. Below the view total when truncated is true.",
"type": [
"number",
"null"
]
},
"table_name": {
"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 not spilled.",
"type": [
"string",
"null"
]
},
"totalCount": {
"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.",
"type": "number"
},
"truncated": {
"description": "True when the CHEMBL_MAX_SPILL_ROWS cap was hit before the upstream view was exhausted — the staged table is a bounded slice, NOT the complete view, so aggregates over it are a sample. Narrow the filters to bring the view under the cap.",
"type": "boolean"
}
},
"type": "object"
}
},
{
"description": "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). 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 upstream request was rejected and the array says nothing about the molecule, and \"truncated\" means the page cap bounded the list at fewer rows than the matching *_total_count.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"molecule_chembl_id": {
"description": "ChEMBL molecule ID (from chembl_search_molecules), e.g. \"CHEMBL939\" for gefitinib.",
"minLength": 1,
"type": "string"
}
},
"required": [
"molecule_chembl_id"
],
"type": "object"
},
"name": "chembl_get_drug_info",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"molecule_chembl_id",
"pref_name",
"max_phase",
"first_approval",
"mechanisms",
"mechanisms_total_count",
"mechanisms_status",
"indications",
"indications_total_count",
"indications_status"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"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.",
"examples": [
"not_found",
"rate_limited"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"first_approval": {
"description": "Year of first approval, e.g. 2003. Null when unapproved or unknown.",
"type": [
"number",
"null"
]
},
"indications": {
"description": "Clinical indications. Empty is authoritative only when indications_status is \"complete\".",
"items": {
"additionalProperties": false,
"description": "One clinical indication with the phase reached for it.",
"properties": {
"efo_term": {
"description": "EFO disease term, e.g. \"non-small cell lung carcinoma\". Null when absent.",
"type": [
"string",
"null"
]
},
"max_phase_for_ind": {
"description": "Max clinical phase reached for THIS indication (1–4). Null when unknown.",
"type": [
"number",
"null"
]
},
"mesh_heading": {
"description": "MeSH disease heading, e.g. \"Carcinoma, Non-Small-Cell Lung\". Null when absent.",
"type": [
"string",
"null"
]
}
},
"required": [
"mesh_heading",
"efo_term",
"max_phase_for_ind"
],
"type": "object"
},
"type": "array"
},
"indications_status": {
"description": "Retrieval state of the indication list. \"complete\" = every row ChEMBL records 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 indications_total_count rows. \"failed\" = the upstream request was rejected, so the empty array is unknown data, NOT evidence that none exist — re-call chembl_get_drug_info to retry.",
"enum": [
"complete",
"truncated",
"failed"
],
"type": "string"
},
"indications_total_count": {
"description": "Total indication rows ChEMBL holds for this molecule (upstream page_meta.total_count). Exceeds the returned array length exactly when the status is \"truncated\". Null when the fetch failed — the count is unknown, never 0.",
"type": [
"number",
"null"
]
},
"max_phase": {
"description": "Max clinical phase across indications: 4 = marketed. Null when unknown.",
"type": [
"number",
"null"
]
},
"mechanisms": {
"description": "Mechanisms of action. Empty is authoritative only when mechanisms_status is \"complete\".",
"items": {
"additionalProperties": false,
"description": "One mechanism of action linked to its molecular target.",
"properties": {
"action_type": {
"description": "Action type, e.g. \"INHIBITOR\", \"AGONIST\", \"ANTAGONIST\". Null when absent.",
"type": [
"string",
"null"
]
},
"mechanism_of_action": {
"description": "Mechanism of action, e.g. \"Epidermal growth factor receptor erbB1 inhibitor\". Null when absent.",
"type": [
"string",
"null"
]
},
"target_chembl_id": {
"description": "ChEMBL target ID the mechanism acts on — chain to chembl_get_bioactivities. Null when unspecified.",
"type": [
"string",
"null"
]
}
},
"required": [
"target_chembl_id",
"mechanism_of_action",
"action_type"
],
"type": "object"
},
"type": "array"
},
"mechanisms_status": {
"description": "Retrieval state of the mechanism list. \"complete\" = every row ChEMBL records 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 upstream request was rejected, so the empty array is unknown data, NOT evidence that none exist — re-call chembl_get_drug_info to retry.",
"enum": [
"complete",
"truncated",
"failed"
],
"type": "string"
},
"mechanisms_total_count": {
"description": "Total mechanism rows ChEMBL holds for this molecule (upstream page_meta.total_count). Exceeds the returned array length exactly when the status is \"truncated\". Null when the fetch failed — the count is unknown, never 0.",
"type": [
"number",
"null"
]
},
"molecule_chembl_id": {
"description": "The ChEMBL molecule ID queried.",
"type": "string"
},
"notice": {
"description": "Disclosure of anything the two lists do not say for themselves: a list whose upstream fetch 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.",
"type": "string"
},
"pref_name": {
"description": "Preferred drug name, e.g. \"GEFITINIB\". Null when unnamed.",
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
{
"description": "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, and max clinical phase 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 capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"cursor": {
"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.",
"type": "string"
},
"limit": {
"description": "Maximum molecules to return. Defaults to the server default (25) when omitted.",
"maximum": 100,
"minimum": 1,
"type": "integer"
},
"max_phase_min": {
"description": "For search_type=name, restrict to compounds at or above this max clinical phase (e.g. 4 for marketed drugs only).",
"maximum": 4,
"minimum": 0,
"type": "integer"
},
"query": {
"description": "Search text for search_type=name — a drug name, ChEMBL ID, or InChIKey, e.g. \"imatinib\" or \"CHEMBL25\".",
"type": "string"
},
"search_type": {
"default": "name",
"description": "name = text lookup (query); exact = exact structure match; similarity = Tanimoto ≥ threshold; substructure = contains the structure. All structure modes need `structure`.",
"enum": [
"name",
"exact",
"similarity",
"substructure"
],
"type": "string"
},
"similarity_threshold": {
"default": 70,
"description": "Minimum Tanimoto similarity percent for search_type=similarity (40–100; ChEMBL rejects below 40). Ignored for other modes.",
"maximum": 100,
"minimum": 40,
"type": "integer"
},
"structure": {
"description": "SMILES string for structure search, e.g. \"CC(=O)Oc1ccccc1C(=O)O\". Required when search_type is exact/similarity/substructure.",
"type": "string"
}
},
"type": "object"
},
"name": "chembl_search_molecules",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"molecules",
"totalCount",
"truncated",
"shown",
"cap"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"cap": {
"description": "The limit that was applied.",
"type": "number"
},
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"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`: 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.",
"examples": [
"not_found",
"rate_limited",
"missing_input"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"molecules": {
"description": "Matching compounds (up to the limit).",
"items": {
"additionalProperties": false,
"description": "A compound matched by the search.",
"properties": {
"alogp": {
"description": "Calculated AlogP lipophilicity, e.g. 1.31. Null when absent.",
"type": [
"number",
"null"
]
},
"canonical_smiles": {
"description": "Canonical SMILES structure. Null when no structure is recorded.",
"type": [
"string",
"null"
]
},
"full_molformula": {
"description": "Molecular formula, e.g. \"C9H8O4\". Null when absent.",
"type": [
"string",
"null"
]
},
"max_phase": {
"description": "Max clinical phase: 4 = marketed drug, 0 = research compound. Null when unknown. The cheap druggability signal.",
"type": [
"number",
"null"
]
},
"molecule_chembl_id": {
"description": "ChEMBL molecule ID, e.g. \"CHEMBL25\". Pass to chembl_get_bioactivities or chembl_get_drug_info.",
"type": "string"
},
"molecule_type": {
"description": "Molecule type, e.g. \"Small molecule\". Null when absent.",
"type": [
"string",
"null"
]
},
"mw_freebase": {
"description": "Molecular weight of the free base in g/mol, e.g. 180.16. Null when absent.",
"type": [
"number",
"null"
]
},
"num_ro5_violations": {
"description": "Lipinski rule-of-five violation count (0–4). Null when not computed.",
"type": [
"number",
"null"
]
},
"pref_name": {
"description": "Preferred name, e.g. \"ASPIRIN\". Null for many research compounds.",
"type": [
"string",
"null"
]
},
"qed_weighted": {
"description": "QED weighted drug-likeness score, 0–1. Null when not computed.",
"type": [
"number",
"null"
]
},
"similarity": {
"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.",
"type": [
"number",
"null"
]
},
"standard_inchi_key": {
"description": "Standard InChIKey — chain to the pubchem server for richer chemistry. Null when absent.",
"type": [
"string",
"null"
]
}
},
"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"
],
"type": "object"
},
"type": "array"
},
"nextCursor": {
"description": "Opaque token for the next page — pass it back as cursor with the same filters. Absent when this page is the last one.",
"type": "string"
},
"notice": {
"description": "Guidance when nothing matched — echoes the query and suggests how to broaden.",
"type": "string"
},
"shown": {
"description": "Number of molecules returned.",
"type": "number"
},
"totalCount": {
"description": "Total compounds matching before the limit was applied.",
"type": "number"
},
"truncated": {
"description": "True when the result was capped at the limit.",
"type": "boolean"
}
},
"type": "object"
}
},
{
"description": "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.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"properties": {
"accession": {
"description": "UniProt accession of a target component, e.g. \"P00533\". The most precise resolver — from the uniprot/protein server.",
"type": "string"
},
"cursor": {
"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.",
"type": "string"
},
"gene_symbol": {
"description": "Gene symbol of a target component, e.g. \"EGFR\" (case-insensitive exact match).",
"type": "string"
},
"limit": {
"description": "Maximum targets to return. Defaults to the server default (25) when omitted.",
"maximum": 100,
"minimum": 1,
"type": "integer"
},
"organism": {
"description": "Restrict to a source organism, e.g. \"Homo sapiens\" (case-insensitive exact match).",
"type": "string"
},
"query": {
"description": "Free-text name match against the target preferred name, e.g. \"kinase\" or \"growth factor receptor\".",
"type": "string"
},
"target_type": {
"description": "Restrict to a target class, e.g. \"SINGLE PROTEIN\" or \"PROTEIN COMPLEX\".",
"type": "string"
}
},
"type": "object"
},
"name": "chembl_search_targets",
"outputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"anyOf": [
{
"not": {
"required": [
"error"
]
},
"required": [
"targets",
"totalCount",
"truncated",
"shown",
"cap"
]
},
{
"required": [
"error"
]
}
],
"properties": {
"cap": {
"description": "The limit that was applied.",
"type": "number"
},
"error": {
"additionalProperties": {},
"description": "Present when the call failed. Absent on success.",
"properties": {
"code": {
"description": "JSON-RPC error code for this failure.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"data": {
"additionalProperties": {},
"properties": {
"reason": {
"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.",
"examples": [
"not_found",
"rate_limited",
"missing_input"
],
"type": "string"
},
"recovery": {
"additionalProperties": {},
"description": "Actionable next step for the caller.",
"properties": {
"hint": {
"type": "string"
}
},
"required": [
"hint"
],
"type": "object"
},
"retryable": {
"description": "Whether retrying may succeed.",
"type": "boolean"
}
},
"type": "object"
},
"message": {
"description": "Human-readable description of what went wrong.",
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object"
},
"nextCursor": {
"description": "Opaque token for the next page — pass it back as cursor with the same filters. Absent when this page is the last one.",
"type": "string"
},
"notice": {
"description": "Guidance when no target matched — echoes the filters and suggests how to broaden.",
"type": "string"
},
"shown": {
"description": "Number of targets returned.",
"type": "number"
},
"targets": {
"description": "Matching targets (up to the limit).",
"items": {
"additionalProperties": false,
"description": "A ChEMBL target resolved from the supplied protein identifier.",
"properties": {
"components": {
"description": "Protein components with UniProt accessions and gene symbols.",
"items": {
"additionalProperties": false,
"description": "One protein component of the target.",
"properties": {
"accession": {
"description": "UniProt accession of the protein component, e.g. \"P00533\". Null when not a protein target.",
"type": [
"string",
"null"
]
},
"gene_symbols": {
"description": "Gene symbols for this component, flattened from component synonyms. Empty when none are recorded.",
"items": {
"description": "A gene symbol for this component, e.g. \"EGFR\".",
"type": "string"
},
"type": "array"
}
},
"required": [
"accession",
"gene_symbols"
],
"type": "object"
},
"type": "array"
},
"organism": {
"description": "Source organism, e.g. \"Homo sapiens\". Null when unspecified.",
"type": [
"string",
"null"
]
},
"pref_name": {
"description": "Preferred target name, e.g. \"Epidermal growth factor receptor\". Null when unnamed.",
"type": [
"string",
"null"
]
},
"target_chembl_id": {
"description": "ChEMBL target ID, e.g. \"CHEMBL203\". Pass to chembl_get_bioactivities as target_chembl_id.",
"type": "string"
},
"target_type": {
"description": "Target class: \"SINGLE PROTEIN\", \"PROTEIN COMPLEX\", \"PROTEIN FAMILY\", \"CELL-LINE\", \"ORGANISM\", etc.",
"type": [
"string",
"null"
]
}
},
"required": [
"target_chembl_id",
"pref_name",
"target_type",
"organism",
"components"
],
"type": "object"
},
"type": "array"
},
"totalCount": {
"description": "Total targets matching the filters before the limit was applied.",
"type": "number"
},
"truncated": {
"description": "True when the result was capped at the limit.",
"type": "boolean"
}
},
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:415db34b2a2512b5d438707071c53ad368f42ac6451675540154e679f3266679 | sha256sum