Chembl Mcp Server

What is Chembl Mcp Server?

Chembl Mcp Server is an unofficial MCP server that provides AI assistants with 22 specialized tools to access the ChEMBL chemical database via its REST API. It enables drug discovery research, chemical informatics, and bioactivity analysis for researchers and developers.

How to use Chembl Mcp Server?

Install Node.js v16+, clone the repository, run npm install then npm run build. Start the server with npm start and add the configuration to your MCP client (e.g., Claude Desktop) specifying the path to build/index.js. Alternatively, you can build and run a Docker container using docker build -t chembl-mcp-server and run it interactively.

Key features of Chembl Mcp Server

• 22 tools for chemical search, target analysis, and bioactivity data
• Compound search by name, synonym, identifier, or InChI
• Target search, pathways, and UniProt integration
• Bioactivity search with dose-response and activity comparison
• Drug development, clinical data, and ADMET analysis
• Substructure search, batch processing, and external references

Use cases of Chembl Mcp Server

• Search for compounds and retrieve detailed chemical properties
• Identify biological targets and find associated compounds
• Analyze bioactivity measurements and dose-response data
• Assess drug-likeness and ADMET properties of candidate molecules
• Batch lookup of multiple ChEMBL IDs for efficient research

FAQ from Chembl Mcp Server

What dependencies are required to run Chembl Mcp Server?

Node.js v16 or higher, npm or yarn, and the npm packages @modelcontextprotocol/sdk, axios, and TypeScript.

How does the server communicate with an MCP client?

It runs as an MCP server that communicates via stdio. You add it to your MCP client configuration (e.g., Claude Desktop) using a command or Docker run command.

Can I use Docker to run Chembl Mcp Server?

Yes, you can build an image with docker build -t chembl-mcp-server and run it with docker run -i chembl-mcp-server. The README provides an example configuration for MCP client integration.

What API does the server connect to?

It connects to the ChEMBL REST API at https://www.ebi.ac.uk/chembl/api/data. Requests include a User-Agent header and a 30-second timeout.

Are there any limits on tool parameters?

The search_compounds and search_activities tools accept a limit parameter from 1 to 1000 (default 25). The batch_compound_lookup tool accepts an array of 1 to 50 ChEMBL IDs.