Crossref MCP Server
About
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.
Details
- Author
- botanicastudios
- GitHub stars
- 3
- Downloads
- 221
- Categories
- Other
Jump to
- 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.
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 ServerCommand (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
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"crossref mcp server": {
"crossref": {
"command": "npx",
"args": [
"-y",
"@botanicastudios/crossref-mcp"
]
}
}
}
}
McpServers
{
"crossref": {
"command": "npx",
"args": [
"-y",
"@botanicastudios/crossref-mcp"
]
}
}
Crossref MCP Server
A Model Context Protocol (MCP) server for interacting with the Crossref API.
Features
- Search works by title
- Search works by author
- Get work details by DOI
Installation
{
"mcpServers": {
"crossref": {
"command": "npx",
"args": [
"-y",
"@botanicastudios/crossref-mcp"
]
}
}
}
Usage
The server provides three main tools:
1. Search by Title
Search for works in Crossref by title:
// Example: Search for works containing "quantum computing" in the title
{
"title": "quantum computing",
"rows": 5 // Optional, defaults to 5
}
2. Search by Author
Search for works in Crossref by author:
// Example: Search for works by "Einstein"
{
"author": "Einstein",
"rows": 5 // Optional, defaults to 5
}
3. Get Work by DOI
Retrieve a specific work using its DOI:
// Example: Get work with DOI "10.1088/1742-6596/1398/1/012023"
{
"doi": "10.1088/1742-6596/1398/1/012023"
}
Response Format
All responses are returned as structured JSON objects with the following format:
For successful searches:
{
"status": "success",
"query": {
/ the original query parameters /
},
"count": 5,
"results": [
{
"title": "Work title",
"authors": [
{
"given": "First name",
"family": "Last name",
"name": "First name Last name"
}
],
"published": {
"dateParts": [2023, 1, 15],
"dateString": "2023-1-15"
},
"type": "journal-article",
"doi": "10.xxxx/xxxxx",
"url": "https://doi.org/10.xxxx/xxxxx",
"container": "Journal Name",
"publisher": "Publisher Name",
"issue": "1",
"volume": "42",
"abstract": "This is the abstract of the work, if available."
}
// additional results...
]
}
For single DOI lookup:
{
"status": "success",
"query": { "doi": "10.xxxx/xxxxx" },
"result": {
// work details as shown above
}
}
For errors or no results:
{
"status": "error" | "no_results" | "not_found",
"message": "Error message" | null,
"query": { / the original query parameters / }
}
Testing
The server comes with a comprehensive test suite using Vitest. Tests cover all available tools and include various scenarios including successful responses, empty results, and error handling.
Running Tests
npm test
Test Structure
The tests use Vitest's mocking capabilities to simulate Crossref API responses without making actual network requests. The test structure includes:
1. Mock Data: Sample responses for title searches, author searches, and DOI lookups
2. Mock Handlers: Testing versions of the handler functions in mcp-server-test-handlers.js
3. Test Cases: Tests for all tools covering:
- Successful API responses
- Empty result sets
- Error handling and network failures
Extending Tests
To add more test cases:
1. Add new mock data to the test file if needed
2. Create additional test cases in the relevant describe block
3. Use the mockFetchResponse() helper to simulate API responses
Example:
it("should handle a new edge case", async () => {
// Mock the response
mockFetchResponse({
// Your sample response data
});
// Call the handler
const result = await handlers.searchByTitle({ title: "example" });
// Assert the expected results
expect(result).toMatchObject({
// Expected response structure
});
});
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



