ChEMBL MCP Server
A Model Context Protocol (MCP) server that exposes ChEMBL's public bioactivity database as tools for searching compounds, retrieving bioactivity data, target compounds, and ADMET properties, usable by Claude and ChatGPT.
README
ChEMBL MCP Server
A Model Context Protocol (MCP) server exposing ChEMBL's public bioactivity database as tools usable by Claude and ChatGPT.
Tools
| Tool | Purpose |
|---|---|
search_compounds |
Search ChEMBL by compound name/synonym |
get_compound_bioactivity |
Get bioactivity records for a ChEMBL ID |
get_target_compounds |
Get active compounds against a target |
get_admet_properties |
Get computed physicochemical/ADMET properties |
Run locally
pip install -r requirements.txt
python3 server.py
Server starts on 0.0.0.0:8000, MCP endpoint at /mcp (streamable HTTP).
IT deployment checklist
- Host: Deploy on a small VM/container (Railway, Render, AWS ECS, or internal cloud). 1 vCPU / 512MB RAM is sufficient — server only proxies to ChEMBL's public REST API, no local DB.
- Public HTTPS: Expose at a subdomain, e.g.
chembl-mcp.excelra.com, with TLS (Let's Encrypt or managed cert). - Reverse proxy: nginx/Caddy → forward to
localhost:8000. - Env/firewall: outbound HTTPS to
www.ebi.ac.ukmust be allowed. - No auth required for MVP (ChEMBL data is public). Add an API key
header check in
server.pylater if you want to gate access.
Connecting to Claude / ChatGPT
- Claude.ai / Claude Desktop: Settings → Connectors → Add custom
connector → enter
https://chembl-mcp.excelra.com/mcp - ChatGPT: Settings → Connectors → Advanced → Developer Mode → Add remote MCP server → same URL
Next steps / extensions
- Add
get_drug_indications,get_similar_compounds(structure similarity) - Cache common ChEMBL responses (Redis) to reduce latency/rate-limit risk
- Swap public REST API for a local ChEMBL Postgres mirror if query volume grows (faster, no rate limits)
- This same scaffold pattern (FastMCP + REST wrapper) is directly reusable for a future GOSTAR MCP server
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.