PubTator-MCP-Server
2
PubTator MCP Server is a tool designed for mining and annotating biomedical literature through an MCP interface, allowing AI models to programmatically search and analyze scientific literature. It offers features like literature annotation export, entity ID lookup, relationship mining, and batch processing to efficiently handle annotation tasks.
PubTator MCP Server
🔍 A biomedical literature annotation and relationship mining server based on PubTator3, providing convenient access through the MCP interface.
✨ Core Features
- Literature Annotation Export: Export PubTator annotation results in multiple formats.
- Entity ID Lookup: Query standard identifiers for biological concepts using free text.
- Relationship Mining: Discover biomedical relationships between entities.
- Literature Search: Retrieve literature by keywords and entity IDs.
- Batch Processing: Export annotation information from search results in batches.
🚀 Quick Start
Requirements
- Python 3.10+
- FastMCP library
Installation
- Via Smithery: Use Smithery for automatic installation.
Manual Installation
- Clone the repository and navigate to it.
- Install dependencies via
pip
.
Running the Server Directly
Configure using environment variables and start the server.
Using Docker
Follow provided instructions to deploy using Docker.
🛠 API Features
- Export Publications
- Entity ID Lookup
- Relationship Query
- Literature Search
- Batch Export
⚠️ Usage Limitations
- API request rate limit: maximum 3 requests per second
- Use a reasonable batch size to avoid timeout
📄 License
MIT License
⚠️ Disclaimer
This tool is for research purposes only. Please comply with PubTator's terms of service.