Crossref MCP Server

by jackkuo666

6 stars

387 downloads

Not rated

GitHub

About

Search and access academic paper metadata from Crossref.

Details

Author: jackkuo666
GitHub stars: 6
Downloads: 387
Categories: Search, Other, Knowledge Base, API
Tags: #research, #document

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Crossref MCP Server

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

From the repository

Install Python 3.10+ and the required dependencies (FastMCP, requests, bs4, habanero). Clone the repository, run pip install -r requirements.txt, then start the server with python crossref_server.py. For use with Claude Desktop or Cline, add the server configuration to cline_mcp_settings.json or claude_desktop_config.json using the appropriate path to Python and the script.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "crossref mcp server": {
            "crossref-MCP-Server": {
                "command": "python",
                "args": [
                    "crossref_server.py"
                ]
            }
        }
    }
}

McpServers

{
    "crossref-MCP-Server": {
        "command": "python",
        "args": [
            "crossref_server.py"
        ]
    }
}

🔍 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 in a programmatic way.

- 🔎 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 and their supported research ✅

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

Add this configuration to yourcline_mcp_settings.jsonorclaude_desktop_config.json:

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

{ "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": [] } } }

The Crossref MCP Server provides the following tools:
- search_works_by_query: Search for scholarly works using keywords, titles, or authors.
- get_work_metadata: Get detailed metadata for a specific work using its DOI.
- search_journals: Search for journals in the Crossref database.
- search_funders: Search for funding organizations in the Crossref database.

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

Can you search Crossref for papers about "machine learning in healthcare"?

You can get detailed metadata for a specific paper using its DOI:

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

You can search for journals in the Crossref database:

Can you find journals related to "artificial intelligence" in Crossref?

You can search for funding organizations:

Can you find information about the "National Science Foundation" in Crossref?

- crossref_server.py: The main MCP server implementation using FastMCP
- crossref_search.py: Contains the logic for searching Crossref and retrieving metadata

- Python 3.10+
- FastMCP (mcp)
- requests
- bs4
- habanero

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License.

This tool uses the Crossref API to access publicly available metadata about academic works. For better API access priority, it's recommended to provide your email address when initializing the CrossrefSearch class.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

A flexible service for searching and analyzing academic papers on arXiv.

Search and cite exact passages across complete classical and world-literature corpora.

Anonymous, read-only, source-backed Buddhist scripture search, passage guidance, explanation, and one-time practice planning through four production MCP tools.

Search and retrieve technical documentation for T&M, industrial automation, and power electronics. Covers everything from oscilloscopes, microcontrollers, vehicles, power supplies, and more from a wide range of manufacturers.

Search and cite the full Pāli Canon (Tipiṭaka, ~444K segments) — Sutta, Vinaya, Abhidhamma at parity with SuttaCentral. Hybrid search, full-sutta fetch, translation comparison, Pāli word lookup. Free, non-commercial, offered as Dhamma Dāna.

Provides MCP tools to search, download, and manage 1M+ research records (papers, images, videos, datasets) from the Compoid AI content repository

MCP server and CLI for managing INCEpTION projects, documents, and exports through the AERO v1 REST API.

This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from Agent Voice Response Wiki.JS instance.

Fetch, convert, and search AWS documentation pages, with recommendations for related content.

Production-ready RAG out of the box to search and retrieve data from your own documents.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Install

More like this

Sequential Thinking

Aws Kb Retrieval Server

Memory

Brave Search

Filesystem

EverArt