Crossref MCP Server

🚀 Crossref MCP Server

Enable AI assistants to search and access academic paper metadata through a simple MCP interface, enabling integration with Crossref.

The Crossref MCP Server serves as a bridge for AI models, allowing them to connect to Crossref's academic literature database via the Model Context Protocol (MCP). It supports searching for scientific papers by DOI, title, or keywords, retrieving their metadata, and programmatically fetching journal and funder information.

✨ Features

• 🔎 Search works by query: Find papers using keywords, titles, or authors ✅
• 📊 Metadata access: Obtain detailed metadata for a specific paper via DOI ✅
• 📚 Journal search: Look up journals in the Crossref database ✅
• 💰 Funder search: Discover funding organizations and the research they support ✅

🚀 Quick Start

Prerequisites

• Python 3.10+
• FastMCP library

Installation

1. Clone the repository:

   git clone https://github.com/JackKuo666/Crossref-MCP-Server.git
   cd Crossref-MCP-Server
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

📊 Usage

Start the MCP server:

python crossref_server.py

Integrating with Claude Desktop or Cline

Add the following configuration to the cline_mcp_settings.json or claude_desktop_config.json file:

(Mac OS)

{
  "mcpServers": {
    "crossref": {
      "command": "python",
      "args": ["-m", "crossref_server.py"]
      }
  }
}

(Windows version):

{
  "mcpServers": {
    "crossref": {
      "command": "C:\\Users\\YOUR\\PATH\\miniconda3\\envs\\mcp_server\\python.exe",
      "args": [
        "D:\\code\\YOUR\\PATH\\Crossref-MCP-Server\\crossref_server.py"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

🛠 MCP Tools

The Crossref MCP Server provides the following tools:

1. search_works_by_query: Search for academic works using keywords, titles, or authors.
2. get_work_metadata: Obtain detailed metadata for a specific paper via DOI.
3. search_journals: Look up journals in the Crossref database.
4. search_funders: Find funding organizations.

Search Works by Query

You can ask the AI assistant to search for papers using keywords:

Can you help me search for papers on "Applications of Machine Learning in Healthcare" on Crossref?

Get Metadata via DOI

You can obtain detailed information for a specific paper via DOI:

Can you show the metadata for the paper with DOI 10.1038/nature14539?

Find Journals

You can look up journals related to "Artificial Intelligence" in the Crossref database:

Can you find journals related to "Artificial Intelligence"?

Find Funders

You can find funding organizations:

Can you provide some information about funding organizations?

Project Structure

• crossref_server.py: The main implementation file for the server.
• crossref_client.py: The client module for interacting with the Crossref API.

Dependencies

• requests: Used for HTTP requests.
• bs4: Used for web page parsing.
• habanero: Used for interacting with the Crossref API.

Contribution

We welcome contributions from the community! Please refer to the project documentation to learn how to participate in the development.

📄 License

This project is licensed under the LICENSE agreement.

📋 Important Note

When using the Crossref API, please ensure that you comply with its terms of service. It is recommended to provide an email address to avoid rate limits.