Biorxiv MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 183 installs a week from npm. Last commit 25 Aug 2026.
Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP.
Today is the operative word: we check Biorxiv MCP Server 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 biorxiv-mcp-server -- npx -y @cyanheads/biorxiv-mcp-server
{
"mcpServers": {
"biorxiv-mcp-server": {
"args": [
"-y",
"@cyanheads/biorxiv-mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.biorxiv-mcp-server]
command = "npx"
args = ["-y", "@cyanheads/biorxiv-mcp-server"]
{
"mcpServers": {
"biorxiv-mcp-server": {
"args": [
"-y",
"@cyanheads/biorxiv-mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"biorxiv-mcp-server": {
"args": [
"-y",
"@cyanheads/biorxiv-mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
BIORXIV_MAILTO (Contact email for User-Agent header — optional, for polite API access.), BIORXIV_WEB_BASE_URL (bioRxiv website base URL — source of rendered full-text HTML pages for biorxiv_get_fulltext.), MEDRXIV_WEB_BASE_URL (medRxiv website base URL — source of rendered full-text HTML pages for biorxiv_get_fulltext.), MCP_HTTP_HOST (The hostname for the HTTP server.), MCP_HTTP_PORT (The port to run the HTTP server on.), MCP_HTTP_ENDPOINT_PATH (The endpoint path for the MCP server.), MCP_AUTH_MODE (Authentication mode to use: 'none', 'jwt', or 'oauth'.), MCP_LOG_LEVEL (Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').).
The author declared them in the registry entry; get the values from the project itself.
MCP server for the HubSpot Integrations Center HubDB: search and retrieve integration data.
The open retrieval layer for AI agents — index code, docs, data. Search via MCP.
bioRxiv + medRxiv preprint server API
Read Project Gutenberg books via MCP. Search, fetch metadata, and retrieve text in passages.
bioRxiv/medRxiv/arXiv preprint full text as structured sections for AI agents + search.
Dry-run-first Google Ads search-term intent analyzer and negative-keyword MCP for agents.
Search live, vetted India jobs by keyword, location, posting age, and job ID.
Search and retrieve job postings on Intermediair (read-only).
Answers built from our own checks of this server.