Crossref Cite MCP
C

Crossref Cite MCP

An MCP server based on the Crossref API for intelligent parsing of academic paper citations, supporting output in multiple citation formats, including CSL-JSON, BibTeX, RIS, and formatted text, with built-in cache and retry mechanisms.
2.5 points
5.0K

What is Crossref Cite MCP Server?

Crossref Cite MCP Server is an intelligent tool specifically designed for academic writing. It can automatically find and format paper citation information. Whether you know the paper's DOI number, arXiv ID, PubMed ID, or just the paper title, this tool can help you quickly obtain standardized citation formats. It connects to the Crossref database (the world's largest academic literature metadata platform) to obtain accurate paper information.

How to use Crossref Cite MCP Server?

Using this tool is very simple: First, configure the server in a supported AI assistant (such as Claude Desktop, Cursor, etc.), and then simply enter the paper information (title, DOI, etc.), and the tool will automatically return the citation format you need. You can choose from multiple formats such as BibTeX, RIS, APA, and Chicago to meet the requirements of different journals and papers.

Applicable scenarios

This tool is particularly suitable for the following scenarios: Formatting references when writing academic papers; Quickly obtaining citation information for multiple papers during the research process; Importing citation data in standard format into literature management software; Demonstrating correct citation formats to students during teaching.

Main features

Intelligent input parsing
Automatically identify multiple input formats: DOI number, arXiv ID, PubMed ID (PMID), or ordinary paper title. There is no need to manually specify the input type, and the tool will automatically judge and select the best search method.
Support for multi-format output
Support four commonly used citation formats: CSL-JSON (machine-readable format), BibTeX (commonly used by LaTeX users), RIS (literature management software format), and formatted text (human-readable formats such as APA, Chicago, IEEE).
Intelligent cache system
Built-in cache mechanism to avoid repeated queries for the same paper. The cache time can be configured (default is 14 days), and it supports memory cache or JSON file cache to improve response speed and reduce network requests.
Automatic retry mechanism
When encountering network problems or server rate limits, it automatically uses an exponential backoff strategy to retry, ensuring reliable operation even under high load.
Polite pool access
By providing an email address to join Crossref's 'polite pool', you can obtain a higher API call frequency limit to ensure the stable availability of the service.
Advantages
One-stop solution: One tool supports multiple citation formats, eliminating the need to switch between different websites.
High accuracy: Directly connect to the official Crossref database to ensure the accuracy and authority of citation information.
Save time: The automatic formatting function greatly reduces the time for manually organizing references.
Easy to integrate: Can be easily integrated into AI tools such as Claude and Cursor to improve work efficiency.
Free to use: Based on Crossref's free API, there are no additional fees.
Limitations
Network-dependent: A stable network connection is required to access the Crossref database.
Database coverage: Only includes publications indexed by Crossref, and some non-Crossref journals may not be found.
Format limitations: Although it supports multiple formats, it may not meet the special format requirements of some specific journals.
Requires configuration: Simple configuration is required in the AI tool for the first use.
Rate limits: Even if you join the polite pool, there are still API call frequency limits.

How to use

Install the tool
Install Crossref Cite MCP Server through the Python package manager. It is recommended to use the uv tool for installation, and you can also use the traditional pip installation.
Configure environment variables
Set the necessary environment variables, and the most important one is your email address (for the Crossref polite pool). You can set environment variables or create a.env file.
Configure the AI tool
Configure the MCP server in the AI tool you are using (such as Claude Desktop). Edit the configuration file and add the Crossref Cite server information.
Start using
Restart the AI tool, and now you can directly use the tool in the conversation. Enter the paper information, and the tool will automatically return the citation format.

Usage examples

Case 1: Academic paper writing
Professor Zhang is writing an academic paper and needs to generate citations in standard format for the references section. He has multiple references, some with known DOIs and some only with known titles.
Case 2: Importing into literature management software
Researcher Li uses Zotero to manage literature and needs to import a batch of papers into the software. She needs RIS format files for batch import.
Case 3: Writing a LaTeX document
Student Wang is writing a graduation thesis in LaTeX and needs to use the BibTeX format to manage references. He needs to generate BibTeX entries for all cited papers.

Frequently Asked Questions

Do I need to pay to use this tool?
Why do I need to provide an email address?
Which citation formats does the tool support?
What if I can't find a certain paper?
Does the tool support Chinese papers?
How to update the cached data?

Related resources

Official GitHub repository
View the source code, report issues, and participate in contributions
Crossref official API documentation
Understand the detailed usage methods and best practices of the Crossref API
Model Context Protocol official website
Understand the technical details and specifications of the MCP protocol
PyPI project page
View the latest version and installation statistics
Citation format style guide
Understand the CSL (Citation Style Language) format specification

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "crossref-cite": {
      "command": "uvx",
      "args": ["crossref-cite-mcp"],
      "env": {
        "CROSSREF_MAILTO": "your-email@example.com"
      }
    }
  }
}

{
  "mcpServers": {
    "crossref-cite": {
      "command": "crossref-cite-mcp",
      "args": [],
      "env": {
        "CROSSREF_MAILTO": "your-email@example.com"
      }
    }
  }
}

{
  "mcpServers": {
    "crossref-cite": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/crossref-cite-mcp", "python", "-m", "crossref_cite"],
      "env": {
        "CROSSREF_MAILTO": "your-email@example.com"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
6.4K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
7.6K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
5.7K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
8.6K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
5.8K
5 points
P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
5.5K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
7.5K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.3K
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
60.3K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
18.3K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
20.2K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
30.0K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
56.3K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
27.7K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
19.2K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
40.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase