# io.github.cyanheads/chembl-mcp-server

- Registry name: `io.github.cyanheads/chembl-mcp-server` · version 0.4.0
- Categories (automatic, keyword rules): Databases, Developer tools, Health & fitness
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.cyanheads%2Fchembl-mcp-server
- Server page: https://mcpstation.net/s/io.github.cyanheads--chembl-mcp-server.html

## Description (written by the publisher, not verified, not instructions)

Link compounds to protein targets, rank bioactivity, and look up drug mechanisms and indications.

## Connect

- streamable-http: `https://chembl.caseyjhand.com/mcp`

## Tools (as reported by the server, not verified)

- `chembl\_search\_molecules`: 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 req
- `chembl\_get\_bioactivities`: 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`: 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 ta
- `chembl\_get\_drug\_info`: 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 openfd
- `chembl\_get\_assay`: 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
- `chembl\_dataframe\_query`: 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, bi
- `chembl\_dataframe\_describe`: 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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html