Skip to main content
MCP server CX Codex

protein-mcp-server — Claude Code MCP server: how to install

Connects AI assistants to experimental and predicted protein databases like RCSB PDB, AlphaFold DB, and UniProt without requiring API tokens.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add --env MCP_LOG_LEVEL=<MCP_LOG_LEVEL> --env MCP_HTTP_HOST=<MCP_HTTP_HOST> --env MCP_HTTP_PORT=<MCP_HTTP_PORT> --env MCP_HTTP_ENDPOINT_PATH=<MCP_HTTP_ENDPOINT_PATH> --env MCP_AUTH_MODE=<MCP_AUTH_MODE> --transport stdio protein-mcp-server -- npx -y protein-mcp-server
Open on GitHub

What protein-mcp-server does

This MCP server exposes 7 tools and 2 URI resources (pdb:// and af://) to inspect macromolecular structures. It aggregates data across RCSB PDB, AlphaFold DB, 3D-Beacons, Foldseek, and InterPro. Clients can query entries via plain text, biological sequences, organisms, or experimental resolution, while also retrieving coordinate URLs.

It handles structural alignment with TM-align and jFATCAT, homolog detection via Foldseek, and ligand binding pocket analysis with contact residues. A sequence search requires at least 10 residues, otherwise the call fails with an invalid_sequence error.

The server runs over STDIO using npx or as an HTTP service, with a public endpoint at https://protein.caseyjhand.com/mcp. Because external credentials are not required, queries run against public biology services immediately upon launch.

What it helps with

  • locate experimental and AlphaFold structures by text query or residue sequence
  • retrieve coordinate URLs and metadata for PDB entries or UniProt IDs
  • run structural alignments using TM-align or jFATCAT
  • map ligand binding pockets and contact distances within macromolecular complexes

Example prompts for the agent

  • Search for human hemoglobin structures with resolution under 2.0 A using protein_search_structures
  • Compare structures 1ABC and 2XYZ using TM-align with protein_compare_structures
  • Inspect the binding site residues for ligand HEM in entry 1A3N using protein_track_ligands

How to install protein-mcp-server

Platform CLI

claude mcp add --env MCP_LOG_LEVEL=<MCP_LOG_LEVEL> --env MCP_HTTP_HOST=<MCP_HTTP_HOST> --env MCP_HTTP_PORT=<MCP_HTTP_PORT> --env MCP_HTTP_ENDPOINT_PATH=<MCP_HTTP_ENDPOINT_PATH> --env MCP_AUTH_MODE=<MCP_AUTH_MODE> --transport stdio protein-mcp-server -- npx -y protein-mcp-server

Replace <…> with your own values

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about protein-mcp-server

How do I install protein-mcp-server in Claude Code?

Run claude mcp add protein-mcp-server -- npx -y protein-mcp-server in your terminal.

Does protein-mcp-server require external API keys?

No API keys are required because the server communicates directly with public repositories like RCSB PDB and AlphaFold DB.

What resources are exposed by the server?

It provides pdb://{entry_id} for experimental PDB records and af://{uniprot} for AlphaFold predictions.

Similar MCP servers

Everything for Science and research →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor