@Augmented-Nature
基本情報
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.
Search PDB database for protein structures by keyword, protein name, or PDB ID
Get detailed information for a specific PDB structure
Download structure coordinates in various formats (PDB, mmCIF, mmTF, XML)
Find PDB structures associated with a UniProt accession
Get structure quality metrics and validation data
A Model Context Protocol (MCP) server that provides programmatic access to the Protein Data Bank (PDB)—the global repository of 3D structures of proteins, nucleic acids, and complex assemblies. It is built for researchers, developers, and bioinformaticians who need to search, retrieve, and analyze macromolecular structures.
Install via npm (npm install && npm build) and configure it as an MCP server in Claude Desktop by adding the built index.js to claude_desktop_config.json. Once configured, you can invoke tools like search_structures, get_structure_info, or download_structure through natural‑language queries, or read resources using URIs such as pdb://structure/{pdb_id}.
It complements the UniProt and AlphaFold MCP servers: this server focuses on experimentally determined structures from PDB, while those servers cover sequence annotations and predicted models respectively.
The server requires Node.js and npm. No external database or API key is needed; it communicates directly with public RCSB PDB APIs.
All data is fetched live from the RCSB Protein Data Bank via their REST, Search, and File Download APIs. No local data is stored by the server.
The server handles invalid PDB IDs, network failures, API rate limiting, missing files, and malformed requests. It does not support user authentication or private data.
The server uses the standard MCP transport (stdio) for local communication with MCP clients like Claude Desktop.
Open-source MCP to use Blender with any LLM
A search tool helps dev to solve the naming things problem.
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Hindsight: Agent Memory That Learns
B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
コメント