ChEMBL
A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database.
What is ChEMBL?
ChEMBL is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to comprehensive model context protocol (mcp) server providing advanced access to the chembl chemical database.
A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database.
This server falls under the Data Science & ML and Databases categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A comprehensive Model Context Protocol (MCP) server providin
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx chembl-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ChEMBL
The ChEMBL MCP Server gives AI assistants direct access to ChEMBL, the open-access biomedical database maintained by EMBL-EBI containing over 2 million drug-like compounds and their biological activity data. It exposes 27 specialized tools spanning chemical search, target analysis, bioactivity assays, drug development data, ADMET property prediction, and advanced substructure search — enabling conversational drug discovery workflows. Medicinal chemists, bioinformaticians, and computational biologists can ask Claude to query compound structures, find similar molecules, retrieve mechanism-of-action data, or assess drug-likeness without writing a single API call.
Prerequisites
- Node.js 18 or later and npm installed
- Git to clone the repository (no npm package is published; must build from source)
- An MCP-compatible client such as Claude Desktop or Cursor
- Internet access to reach the ChEMBL REST API (no API key required)
Clone the repository
Clone the ChEMBL MCP Server repository from GitHub. No pre-built npm package is available, so you must build it locally.
git clone https://github.com/Augmented-Nature/ChEMBL-MCP-Server.git
cd ChEMBL-MCP-ServerInstall dependencies and build
Install Node.js dependencies and compile the TypeScript source to JavaScript. The build output goes to the build/ directory.
npm install
npm run buildNote the absolute path to the built server
Record the full absolute path to the compiled entry point. You will need this in your MCP client config.
pwd
# e.g., /Users/you/ChEMBL-MCP-Server
# Entry point: /Users/you/ChEMBL-MCP-Server/build/index.jsConfigure your MCP client
Open your MCP client configuration file and add the chembl server entry, replacing the path with the actual location of your build/index.js file.
{
"mcpServers": {
"chembl": {
"command": "node",
"args": ["/Users/you/ChEMBL-MCP-Server/build/index.js"],
"env": {}
}
}
}Restart your MCP client and verify
Save the config and restart your MCP client. All 27 ChEMBL tools should appear. Try asking Claude about a compound like aspirin to confirm the connection is working.
ChEMBL Examples
Client configuration
Claude Desktop configuration pointing to a locally built ChEMBL MCP Server. No API key is needed — ChEMBL data is freely available.
{
"mcpServers": {
"chembl": {
"command": "node",
"args": ["/Users/you/ChEMBL-MCP-Server/build/index.js"],
"env": {}
}
}
}Prompts to try
Example prompts that leverage the 27 ChEMBL tools for drug discovery research.
- "Search ChEMBL for compounds similar to aspirin and compare their drug-likeness scores"
- "Find all targets associated with imatinib and show their pathways"
- "Look up the mechanism of action for sildenafil and list its approved indications"
- "Get the ADMET properties for CHEMBL25 and flag any red flags for oral bioavailability"
- "Run a substructure search for molecules containing a sulfonamide group and return the top 10 most potent against kinase targets"
- "Compare the IC50 values for known CDK2 inhibitors across all available bioactivity assays"Troubleshooting ChEMBL
build/index.js not found after npm run build
Ensure npm install completed without errors first. Check that TypeScript compiled successfully by looking for error output during 'npm run build'. The output directory is 'build/' relative to the repo root.
Tools return network errors or timeouts
The server queries the ChEMBL REST API (www.ebi.ac.uk/chembl/api). Verify you have internet access and that the ChEMBL API is reachable. The API has rate limits; avoid sending many large batch requests in rapid succession.
MCP client cannot connect to the server
Make sure the path in args points to the absolute path of build/index.js. Relative paths do not work in MCP client configs. Run 'node /path/to/build/index.js' in a terminal to confirm it starts without errors.
Frequently Asked Questions about ChEMBL
What is ChEMBL?
ChEMBL is a Model Context Protocol (MCP) server that comprehensive model context protocol (mcp) server providing advanced access to the chembl chemical database. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ChEMBL?
Follow the installation instructions on the ChEMBL GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ChEMBL?
ChEMBL works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ChEMBL free to use?
Yes, ChEMBL is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
ChEMBL Alternatives — Similar Data Science & ML Servers
Looking for alternatives to ChEMBL? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ChEMBL in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ChEMBL?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.