Structural Biology MCP Server
Enables interaction with the RCSB Protein Data Bank to search, analyze, and visualize protein structures. It provides specialized tools for downloading coordinate files and performing structural modifications like residue mutations and metal atom replacements.
README
Structural Biology MCP Agent
An AI agent for structural biology that uses Model Context Protocol (MCP) to search, analyze, modify, and visualize protein structures from the RCSB Protein Data Bank.
Architecture
User (browser)
|
Streamlit Chat UI (protein_chat_mcp.py)
|
Claude AI (decides which tools to call)
|
MCP Client (standard protocol)
|
PDB MCP Server (pdb_mcp_server.py) ── 11 tools
|
RCSB PDB APIs
Why MCP? MCP is a standard protocol for AI-tool communication. Instead of hardcoding tools inside the app, the MCP server exposes tools that any MCP-compatible AI client can discover and use automatically — Claude Code, Cursor, or this custom Streamlit app.
11 Tools
| # | Tool | Description |
|---|---|---|
| 1 | search_structures |
Search PDB by keyword, filter by method/resolution |
| 2 | get_structure_info |
Get detailed metadata for a PDB ID |
| 3 | download_structure |
Download PDB coordinate files |
| 4 | search_by_uniprot |
Find structures linked to a UniProt accession |
| 5 | get_structure_quality |
Resolution, R-factors, Ramachandran validation |
| 6 | replace_metal |
Swap metals in HETATM records (e.g., Co → Zn) |
| 7 | mutate_residue |
Mutate amino acids (e.g., HIS93 → SER) |
| 8 | remove_hetatm |
Remove specific ligands/heteroatoms |
| 9 | remove_chain |
Remove a chain from a multi-chain structure |
| 10 | list_hetatm |
List all ligands/heteroatoms in a structure |
| 11 | get_modified_structure |
Retrieve a modified PDB file |
Demo
Ask the chat app:
"Download 1YOG, replace cobalt with zinc, and show me the structure"
Claude automatically chains 3 MCP tool calls:
download_structure("1YOG")→ fetches PDB filereplace_metal("1YOG", "CO", "ZN")→ swaps Co→Zn in HETATM recordsshow_structure_3d("1YOG_ZN")→ renders interactive 3D viewer
Quick Start
1. Install dependencies
pip install "mcp[cli]" requests streamlit anthropic py3Dmol
2. Run the chat app
cd protein_chat
streamlit run protein_chat_mcp.py
Enter your Anthropic API key in the sidebar. Start chatting about protein structures.
3. Or use with Claude Code directly
claude mcp add pdb-server python /path/to/pdb_mcp_server.py
Then ask Claude Code: "Search PDB for cryoEM spike protein structures under 3A resolution"
Project Structure
structural-biology-mcp/
pdb_mcp_server.py # MCP server (11 tools)
protein_chat/
protein_chat_mcp.py # Streamlit chat app (MCP client)
.streamlit/config.toml # Dark theme config
requirements.txt # Python dependencies
PDB_MCP_Server_Tutorial.ipynb # Tutorial notebook
requirements.txt # Server dependencies
APIs Used
- RCSB PDB Data API - Structure metadata
- RCSB PDB Search API - Full-text and attribute search
- RCSB PDB Files - Coordinate file downloads
Requirements
- Python 3.10+
mcp[cli]>= 1.0anthropic>= 0.40.0streamlit>= 1.37.0py3Dmolrequests
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.