Crossref MCP Server

Name: Crossref MCP Server
Author: botanicastudios

@botanicastudios

Repository

About Crossref MCP Server

MCP server for Crossref

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "crossref": {
      "command": "npx",
      "args": [
        "-y",
        "@botanicastudios/crossref-mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Crossref MCP Server?

A Model Context Protocol (MCP) server that provides tools for searching and retrieving scholarly works from the Crossref API. It is intended for developers integrating publication metadata into AI assistants or other applications.

How to use Crossref MCP Server?

Install by adding the server to your mcpServers configuration using npx -y @botanicastudios/crossref-mcp. Once configured, the server exposes three tools: searchByTitle, searchByAuthor, and getWorkByDOI. Each tool takes specific parameters (e.g., title, author, doi) and returns structured JSON results.

Key features of Crossref MCP Server

Search works by title (with configurable result count).
Search works by author (with configurable result count).
Retrieve detailed work metadata by DOI.
Structured JSON response with status, query, and results.
Built-in test suite using Vitest with mocked API calls.

Use cases of Crossref MCP Server

Finding academic papers by title or author name.
Fetching complete citation details (authors, journal, date) for a given DOI.
Integrating publication search into AI‑powered research assistants.
Validating or enriching bibliographic references programmatically.

FAQ from Crossref MCP Server

What tools does Crossref MCP Server provide?

It provides three tools: searchByTitle, searchByAuthor, and getWorkByDOI.

How many results are returned by default?

The default number of results for title and author searches is 5. The rows parameter can be used to change this.

What does the response look like in case of an error?

Errors return a JSON object with a status field set to error, no_results, or not_found, along with an optional message and the original query.