Biorxiv Mcp Server
by cyanheadscommunityv0.1.15
1
An MCP server for searching and retrieving bioRxiv and medRxiv preprints by DOI, date interval, or keyword. It also resolves preprints to journal publication records and lists valid subject categories.
From the registry: Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP.
Install & configure
Prerequisites
- requiredInstall Node.js or BunInstall Node.js v24+ or Bun v1.3.2+ to run the server. The simplest portable path in the README uses npx, so Node.js is sufficient.https://nodejs.org/
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `biorxiv-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js or Bun** — Install Node.js v24+ or Bun v1.3.2+ to run the server. The simplest portable path in the README uses npx, so Node.js is sufficient. (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@cyanheads/biorxiv-mcp-server@latest"]
- required environment variables:
- `MCP_TRANSPORT_TYPE`: Transport mode for the server. Use stdio for MCP client config. (example: `stdio`)
- optional environment variables:
- `MCP_LOG_LEVEL`: Log level for server output. (example: `info`)
- `BIORXIV_MAILTO`: Email address included in the User-Agent header for polite API access per Cold Spring Harbor Lab guidelines. Recommended by the README but marked optional. (example: `<your-email@example.com>`)
- `BIORXIV_API_BASE_URL`: Override the bioRxiv API base URL. (example: `<your-biorxiv-api-base-url>`)
- `EUROPEPMC_API_BASE_URL`: Override the EuropePMC API base URL. (example: `<your-europepmc-api-base-url>`)
- `CANVAS_PROVIDER_TYPE`: Set to duckdb to enable DataCanvas spillover for large result sets (Node only). (example: `duckdb`)
- `MCP_HTTP_PORT`: HTTP server port when using HTTP transport. (example: `<your-http-port>`)
- `MCP_HTTP_ENDPOINT_PATH`: HTTP endpoint path when using HTTP transport. (example: `<your-http-endpoint-path>`)
- `MCP_AUTH_MODE`: Authentication mode: none, jwt, or oauth. (example: `none`)
- `LOGS_DIR`: Directory for log files (Node.js only). (example: `<your-logs-directory>`)
- `OTEL_ENABLED`: Enable OpenTelemetry instrumentation. (example: `false`)
Note: The README also supports Streamable HTTP transport, started separately with MCP_TRANSPORT_TYPE=http; however, the simplest canonical MCP client configuration shown is stdio via npx.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: The README also supports Streamable HTTP transport, started separately with MCP_TRANSPORT_TYPE=http; however, the simplest canonical MCP client configuration shown is stdio via npx.
Tools (5)
biorxiv_get_preprint
Fetch full metadata, abstract, revision history, and journal crosswalk for one or more preprints by DOI
biorxiv_list_recent
List preprints posted or updated within a date interval, with optional server and category filters
biorxiv_search_preprints
Search preprints by keyword via EuropePMC for relevance ranking, enriched with bioRxiv/medRxiv metadata
biorxiv_get_published_version
Resolve a preprint DOI to its journal publication record, including journal DOI, name, and published date
biorxiv_list_categories
List valid subject category strings for bioRxiv and medRxiv
Environment variables
BIORXIV_MAILTOEmail address included in the User-Agent header for polite API accessPrerequisites
- • Node.js v24+
Packages
@cyanheads/biorxiv-mcp-server
npmv0.1.15transport: stdio
@cyanheads/biorxiv-mcp-server
npmv0.1.15transport: streamable-http
Details
- Language
- TypeScript
- License
- NOASSERTION
- Released
- Jun 20, 2026
- Last commit
- Jun 20, 2026
- Registry name
- io.github.cyanheads/biorxiv-mcp-server