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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。