io.github.cyanheads/chembl-mcp-server

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. Requires CANVAS_PROVIDER_TYPE=duckdb.

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.

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.

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. 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 requires CANVAS_PROVIDER_TYPE=duckdb. 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.

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.

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.

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.