AlphaFold MCP
A comprehensive Model Context Protocol (MCP) server that provides access to the AlphaFold Protein Structure Database through a rich set of tools and resources for protein structure prediction analysis.
What is AlphaFold MCP?
AlphaFold MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to comprehensive model context protocol (mcp) server that provides access to the alphafold protein structure database through a rich set of tools and resources for protein structure prediction analysis....
A comprehensive Model Context Protocol (MCP) server that provides access to the AlphaFold Protein Structure Database through a rich set of tools and resources for protein structure prediction analysis.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A comprehensive Model Context Protocol (MCP) server that pro
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx alphafold-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AlphaFold MCP
The AlphaFold MCP Server provides a rich programmatic interface to the AlphaFold Protein Structure Database hosted by EMBL-EBI. It lets AI assistants retrieve predicted protein structures by UniProt ID, run per-residue confidence scoring, batch-process up to 50 proteins at once, and export data formatted for molecular visualization tools like PyMOL and ChimeraX. Researchers in drug discovery, structural biology, and bioinformatics can use this server to fold protein analysis questions into conversational AI workflows without writing custom API clients.
Prerequisites
- Node.js 18 or later
- npm (comes with Node.js)
- Internet access to reach https://alphafold.ebi.ac.uk/api/ (no API key required)
- An MCP client such as Claude Desktop
Clone the repository
Download the server source code from GitHub.
git clone https://github.com/Augmented-Nature/AlphaFold-MCP-Server.git && cd AlphaFold-MCP-ServerInstall dependencies
Install Node.js packages required by the server.
npm installBuild the server
Compile the TypeScript source to the build/ directory.
npm run buildTest the server locally
Run the compiled server to confirm it starts without errors before wiring it into a client.
node build/index.jsAdd the server to your MCP client
Add the configuration block shown below to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json), replacing /path/to with your actual clone location. Restart the client.
AlphaFold MCP Examples
Client configuration
Reference the compiled index.js using an absolute path. No API key is needed — the server calls the public AlphaFold EBI API.
{
"mcpServers": {
"alphafold-server": {
"command": "node",
"args": ["/absolute/path/to/AlphaFold-MCP-Server/build/index.js"]
}
}
}Prompts to try
Representative queries that exercise structure retrieval, confidence analysis, and batch processing.
- "Check whether AlphaFold has a prediction for UniProt ID P04637 (human TP53)"
- "Download the PDB file for UniProt P53350 and describe the high-confidence regions"
- "Run a batch confidence analysis on P04637, P53350, and P63151 and tell me which has the most disordered regions"
- "Find AlphaFold entries for BRCA1 in Homo sapiens"
- "Export the structure of Q8N3R9 in ChimeraX format with confidence colouring"Troubleshooting AlphaFold MCP
node build/index.js exits immediately or throws 'Cannot find module'
Run 'npm run build' again and confirm a build/ directory with index.js was created. Also verify you are on Node.js 18+ with 'node --version'.
Batch requests return partial results or rate-limit errors
The server automatically chunks requests and enforces rate limits. Batch downloads are capped at 20 proteins and analysis batches at 30-50. Split larger lists into multiple prompts.
UniProt ID returns 'no prediction available'
Not all proteins in UniProt have AlphaFold entries. Use the search tools to find available entries by protein name or organism before requesting a specific ID.
Frequently Asked Questions about AlphaFold MCP
What is AlphaFold MCP?
AlphaFold MCP is a Model Context Protocol (MCP) server that comprehensive model context protocol (mcp) server that provides access to the alphafold protein structure database through a rich set of tools and resources for protein structure prediction analysis. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AlphaFold MCP?
Follow the installation instructions on the AlphaFold MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AlphaFold MCP?
AlphaFold MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AlphaFold MCP free to use?
Yes, AlphaFold MCP is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
AlphaFold MCP Alternatives — Similar Data Science & ML Servers
Looking for alternatives to AlphaFold MCP? 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 AlphaFold MCP 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 AlphaFold MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.