ChEMBL MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_compoundsC | Search ChEMBL database for compounds by name, synonym, or identifier |
| get_compound_infoC | Get detailed information for a specific compound by ChEMBL ID |
| search_by_inchiC | Search for compounds by InChI key or InChI string |
| get_compound_structureB | Retrieve chemical structure information in various formats |
| search_similar_compoundsB | Find chemically similar compounds using Tanimoto similarity |
| search_targetsC | Search for biological targets by name or type |
| get_target_infoC | Get detailed information for a specific target by ChEMBL target ID |
| get_target_compoundsC | Get compounds tested against a specific target |
| search_by_uniprotC | Find ChEMBL targets by UniProt accession |
| get_target_pathwaysC | Get biological pathways associated with a target |
| search_activitiesC | Search bioactivity measurements and assay results |
| get_assay_infoC | Get detailed information for a specific assay by ChEMBL assay ID |
| search_by_activity_typeB | Find bioactivity data by specific activity type and value range |
| get_dose_responseC | Get dose-response data and activity profiles for compounds |
| compare_activitiesC | Compare bioactivity data across multiple compounds or targets |
| search_drugsC | Search for approved drugs and clinical candidates |
| get_drug_infoB | Get drug development status and clinical trial information |
| search_drug_indicationsC | Search for therapeutic indications and disease areas |
| get_mechanism_of_actionB | Get mechanism of action and target interaction data |
| analyze_admet_propertiesC | Analyze ADMET properties (Absorption, Distribution, Metabolism, Excretion, Toxicity) |
| calculate_descriptorsC | Calculate molecular descriptors and physicochemical properties |
| predict_solubilityC | Predict aqueous solubility and permeability properties |
| assess_drug_likenessB | Assess drug-likeness using Lipinski Rule of Five and other metrics |
| substructure_searchC | Find compounds containing specific substructures |
| batch_compound_lookupC | Process multiple ChEMBL IDs efficiently |
| get_external_referencesB | Get links to external databases (PubChem, DrugBank, PDB, etc.) |
| advanced_searchC | Complex queries with multiple chemical and biological filters |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 27 tools
Most tools have distinct purposes, such as 'get_compound_info' for compound details versus 'calculate_descriptors' for molecular properties, but some overlap exists, like 'search_compounds' and 'search_by_inchi', which could cause confusion as both search for compounds using different identifiers. Descriptions help clarify, but the overlap in search functionality is noticeable.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'get_compound_info', 'search_targets', and 'predict_solubility'. This uniformity makes the tool set predictable and easy to navigate, with no deviations in naming conventions.
With 27 tools, the count is borderline high for a single server, potentially overwhelming for agents, but it aligns with the comprehensive scope of a chemical and biological database like ChEMBL. It feels heavy but not extreme, as the domain justifies many specialized operations.
The tool set provides complete coverage for the ChEMBL domain, including compound and target information retrieval, search capabilities, ADMET analysis, and drug development data. There are no obvious gaps; agents can perform full workflows from discovery to analysis without dead ends.