Crossref-MCP-Server
The Crossref MCP Server enables AI assistants to access and search Crossref's academic paper metadata using the Model Context Protocol (MCP). It supports searching by various parameters and retrieving detailed metadata, journals, and funder information programmatically. The project is built for seamless integration with AI models.
Crossref MCP Server
Enable AI assistants to search and access academic paper metadata through Crossref using a simple MCP interface. The Crossref MCP Server provides a bridge between AI assistants and Crossref's database of academic literature through the Model Context Protocol (MCP). It allows AI models to search for scientific articles by DOI, title, or keywords, access their metadata, and retrieve journal and funder information programmatically.
Core Features
- Work Search by Query: Find papers using keywords, titles, or authors
- Metadata Access: Retrieve detailed metadata for specific papers by DOI
- Journal Search: Find journals in the Crossref database
- Funder Search: Discover funding organizations
Quick Start
Prerequisites
- Python 3.10+
- FastMCP library
Installation
- Clone the repository
- Install the required dependencies
Usage
Start the MCP server and configure for use with Claude Desktop or Cline.
MCP Tools
search_works_by_query
get_work_metadata
search_journals
search_funders
Project Structure
crossref_server.py
: The main MCP server implementation using FastMCPcrossref_search.py
: Contains the logic for searching Crossref and retrieving metadata
Dependencies
- Python 3.10+
- FastMCP (mcp)
- requests
- bs4
- habanero
Contributing
Contributions are welcome. Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License.
Note
This tool uses the Crossref API for accessing publicly available metadata, and including your email in the initialization improves API access priority.