PubTator MCP Server
by JackKuo666
PubTator MCP Server provides AI assistants with access to the PubTator3 biomedical literature annotation system through the Model Context Protocol (MCP). It allows AI models to programmatically search scientific literature, obtain annotation information, and analyze entity relationships.
Last updated: N/A
What is PubTator MCP Server?
PubTator MCP Server is a server that provides access to the PubTator3 biomedical literature annotation system through the Model Context Protocol (MCP). It enables AI models to search scientific literature, obtain annotation information, and analyze entity relationships programmatically.
How to use PubTator MCP Server?
The server can be installed either manually or through Smithery. After installation, it can be run directly using Python or deployed using Docker. Configuration options are available for various clients like Claude and CLine, allowing customization of transport protocols, host, and port.
Key features of PubTator MCP Server
Literature Annotation Export: Support exporting PubTator annotation results in multiple formats
Entity ID Lookup: Query standard identifiers for biological concepts through free text
Relationship Mining: Discover biomedical relationships between entities
Literature Search: Support literature retrieval by keywords and entity IDs
Batch Processing: Support batch export of annotation information from search results
Use cases of PubTator MCP Server
Enabling AI assistants to access and analyze biomedical literature.
Programmatically searching for scientific literature related to specific entities.
Extracting annotation information from scientific articles.
Discovering relationships between biomedical entities like genes, diseases, and chemicals.
FAQ from PubTator MCP Server
What is the API request rate limit?
What is the API request rate limit?
The API request rate limit is a maximum of 3 requests per second.
What should I consider when batch exporting?
What should I consider when batch exporting?
When batch exporting, use a reasonable batch_size to avoid request timeout.
How should entity IDs be formatted for relationship queries?
How should entity IDs be formatted for relationship queries?
For relationship queries, entity IDs must start with "@", e.g., "@DISEASE_COVID-19".
What license is this project under?
What license is this project under?
This project is licensed under the MIT License.
What is the purpose of this tool?
What is the purpose of this tool?
This tool is for research purposes only. Please comply with PubTator's terms of service and use this tool responsibly.