Crossref MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 75 installs a week from pypi. Last commit 8 Jun 2026.
MCP server wrapping the Crossref REST API for scholarly metadata.
Today is the operative word: we check Crossref MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add crossref-mcp -- uvx crossref-mcp
{
"mcpServers": {
"crossref-mcp": {
"args": [
"crossref-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.crossref-mcp]
command = "uvx"
args = ["crossref-mcp"]
{
"mcpServers": {
"crossref-mcp": {
"args": [
"crossref-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"crossref-mcp": {
"args": [
"crossref-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
CROSSREF_MAILTO (Email for Crossref's polite pool (recommended).), CROSSREF_PLUS_TOKEN (Optional Crossref Plus API token.).
The author declared them in the registry entry; get the values from the project itself.
Search and retrieve scholarly metadata from the Crossref REST API
MCP server wrapping the Tesla Fleet API and TeslaMate API
MCP server for consuming and managing Groups.io data via the Groups.io REST API
Calendly MCP Pack — wraps the Calendly API v2 for scheduling data.
MCP server wrapping the nb CLI for LLM-friendly note-taking
Crossref MCP — wraps the Crossref REST API (academic papers, free, no auth)
MCP server for web scraping: URLs, links, metadata, CSS extraction.
MCP server for the Keeping time-tracking API
Answers built from our own checks of this server.