# protein-mcp-server

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

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: cyanheads
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cyanheads/protein-mcp-server
- Updated: 2026-10-17
- HTML: https://affpapa.org/en/nevibecode/mcp/protein-mcp-server

## What it 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.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `MCP_LOG_LEVEL`, `MCP_HTTP_HOST`, `MCP_HTTP_PORT`, `MCP_HTTP_ENDPOINT_PATH`, `MCP_AUTH_MODE` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
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

### Codex

**Platform CLI**
```bash
codex mcp add protein-mcp-server --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> -- npx -y protein-mcp-server
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "protein-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "protein-mcp-server"
            ],
            "env": {
                "MCP_LOG_LEVEL": "<MCP_LOG_LEVEL>",
                "MCP_HTTP_HOST": "<MCP_HTTP_HOST>",
                "MCP_HTTP_PORT": "<MCP_HTTP_PORT>",
                "MCP_HTTP_ENDPOINT_PATH": "<MCP_HTTP_ENDPOINT_PATH>",
                "MCP_AUTH_MODE": "<MCP_AUTH_MODE>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "protein-mcp-server": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "protein-mcp-server"
            ],
            "env": {
                "MCP_LOG_LEVEL": "<MCP_LOG_LEVEL>",
                "MCP_HTTP_HOST": "<MCP_HTTP_HOST>",
                "MCP_HTTP_PORT": "<MCP_HTTP_PORT>",
                "MCP_HTTP_ENDPOINT_PATH": "<MCP_HTTP_ENDPOINT_PATH>",
                "MCP_AUTH_MODE": "<MCP_AUTH_MODE>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e MCP_LOG_LEVEL=<MCP_LOG_LEVEL> -e MCP_HTTP_HOST=<MCP_HTTP_HOST> -e MCP_HTTP_PORT=<MCP_HTTP_PORT> -e MCP_HTTP_ENDPOINT_PATH=<MCP_HTTP_ENDPOINT_PATH> -e MCP_AUTH_MODE=<MCP_AUTH_MODE> protein-mcp-server npx -y protein-mcp-server
```
Replace <…> with your own values

## When to use it
- 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
- 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

## Similar
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5585
- [arxiv-mcp-server](https://affpapa.org/en/nevibecode/mcp/arxiv-mcp-server.md) — MCP server · ★ 3235
- [PaperBanana](https://affpapa.org/en/nevibecode/mcp/paperbanana.md) — MCP server · ★ 2418
- [MATLAB MCP Server](https://affpapa.org/en/nevibecode/mcp/matlab-mcp-server.md) — MCP server · ★ 1723
- [Hex Research](https://affpapa.org/en/nevibecode/mcp/hex-research.md) — MCP server · ★ 584
- [DocsAgent — Zotero, Obsidian & Apple Notes MCP Server](https://affpapa.org/en/nevibecode/mcp/docsagent-zotero-obsidian-apple-notes-mcp-server.md) — MCP server · ★ 578

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md