AlphaFold
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.
claude mcp add --transport stdio augmented-nature-alphafold-mcp-server node /path/to/alphafold-server/build/index.js
How to use
The AlphaFold MCP Server provides programmatic access to the AlphaFold Protein Structure Database through a rich set of tools for retrieval, analysis, batch processing, and visualization preparation. You can discover, fetch, and compare predicted structures by UniProt ID, search for proteins by name or organism, evaluate per-residue confidence scores, and generate export-ready formats for PyMOL or ChimeraX. The server exposes a collection of MCP tools such as get_structure, download_structure, check_availability, search_structures, get_confidence_scores, batch_structure_info, batch_download, compare_structures, find_similar_structures, and export_for_pymol/export_for_chimerax, enabling streamlined workflows from discovery to visualization-ready data.
How to install
Prerequisites:\n- Node.js (and npm) installed on your system.\n- Access to the repository hosting the AlphaFold MCP Server.\n\nInstallation steps:\n1) Clone or create the server directory:\n git clone <repository-url> alphafold-server\n cd alphafold-server\n\n2) Install dependencies:\n npm install\n\n3) Build the server (if a build step is required by the project):\n npm run build\n\n4) Run the server (as a local MCP server):\n npm start\n // Or start directly if you run the built file:\n node build/index.js\n\nNote: The MCP configuration for integrating this server into an MCP platform should reference the server entry as shown in the mcp_config section.
Additional notes
Tips and considerations:\n- Ensure Node.js runtime matches the server’s compatibility (check package.json for engines).\n- The MCP config uses the server name alphafold-server; ensure consistency across your platform.\n- When retrieving large batches, leverage batch_* tools to minimize round-trips and optimize throughput.\n- For visualization exports, confirm that downstream tools (PyMOL/ChimeraX) are prepared to consume the exported formats.\n- If the server cannot reach AlphaFold data sources, verify network access and any API endpoints or data mirrors used by the implementation.\n- Environment variables you may need to configure (placeholders):\n - ALPHAFOLD_API_BASE_URL: Base URL for AlphaFold API (if applicable).\n - LOG_LEVEL: Information, debug, or warning level for verbose logs.\n - DATA_CACHE_DIR: Path to cache downloaded structures to improve performance.
Related MCP Servers
mcp-for-beginners
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
bitbucket
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs
ChEMBL
A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database.
crawlbase
Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.
PDB
A Model Context Protocol (MCP) server that provides access to the Protein Data Bank (PDB) - the worldwide repository of information about the 3D structures of proteins, nucleic acids, and complex assemblies.
Augmented-Nature-UniProt
A comprehensive Model Context Protocol (MCP) server providing advanced access to the UniProt protein database.