Biorxiv Mcp Server

---

Overview

bioRxiv and medRxiv preprint metadata and full text, searchable via EuropePMC. Fetch preprints by DOI, browse by date interval or subject category, search by keyword and author, resolve journal-publication crosswalks, and extract full text from the rendered article page, from any MCP client. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

Tool	Description
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 and/or author via EuropePMC for relevance ranking, enriched with bioRxiv/medRxiv metadata
biorxiv_get_published_version	Resolve a preprint DOI to its journal publication record (journal DOI, name, published date)
biorxiv_get_fulltext	Retrieve a preprint's full text as best-effort Markdown extracted from its rendered HTML article page
biorxiv_list_categories	List valid subject category strings for bioRxiv and medRxiv

Capability reference

biorxiv_get_preprint _tool

• Batch fetch up to 10 DOIs in a single request
• Each DOI returns its full revision history in revisions[] — one API call per DOI, no enumeration loop
• Includes title, authors, abstract, category, license, JATS XML full-text link (jatsxmlUrl), and published journal DOI (publishedJournalDoi) once accepted
• Scope to biorxiv, medrxiv, or both (default both); when both, each DOI fans out in parallel and partial failures report per-DOI in failed[]
• Each failed[] entry carries a reason (not_found, invalid_doi_format, upstream_unavailable, rate_limited) and a retryable flag — a DOI is only reported not_found when every attempted server answered
• A rate-limited lookup (HTTP 429) reports reason: "rate_limited" rather than folding into upstream_unavailable, carrying retryAfter — the wait in seconds api.biorxiv.org asked for

---

biorxiv_list_recent _tool

• Optional server-side category filter — pass a value from biorxiv_list_categories
• Fixed page size of 30 (API constraint); advance with integer cursor (0, 30, 60, …)
• Response includes a total count per server; a cursor past the last page is marked exhausted: true rather than reading as zero results in the interval
• When server="both" (default), per-server pagination state is independent ({ biorxiv: { cursor, total }, medrxiv: { cursor, total } }); one server not answering is named in failed[] while the other's page still returns
• Every attempted server failing raises a retryable upstream_unavailable (or rate_limited) error instead of an empty page

---

biorxiv_search_preprints _tool

• Query and/or author required (author maps to an EuropePMC AUTH:"…" field query, ANDed with the keyword query); optional date_from/date_to range and server scope (default both)
• Up to 100 results per page (default 25); cursor_mark pages through the same ranked list
• EuropePMC powers relevance ranking (indexes new preprints within 1–2 days of posting); the bioRxiv/medRxiv API enriches matches with canonical metadata
• Enriched results carry the same latest-revision fields as biorxiv_get_preprint, including type, license, funder, and authorCorrespondingInstitution
• Enrichment failures degrade to EuropePMC-only metadata, surfaced via partial_results and a per-record enrichment_error (service_error, rate_limited, or not_found)
• A EuropePMC rate limit (HTTP 429) raises a retryable rate_limited error carrying the origin's Retry-After wait — the search itself has no metadata to fall back on, unlike enrichment

---

biorxiv_get_published_version _tool

• Uses the /pubs/{server}/{doi} endpoint for richer metadata than the publishedJournalDoi field on biorxiv_get_preprint
• Returns journal DOI, journal name, published date, and corresponding-author institution; the output server field names which server answered (never "both")
• Scope to biorxiv, medrxiv, or both (default both) — the two servers share the 10.1101/ DOI prefix, so a DOI alone doesn't identify one
• No server answering raises a retryable upstream_unavailable, or rate_limited with the origin's wait on an HTTP 429 — never doi_not_found, which would assert an absence nothing established

---

biorxiv_get_fulltext _tool

• Fetches the rendered HTML article page (www.{server}.org/content/{doi}v{N}.full) and extracts Markdown — there is no keyless JATS source
• Resolves the latest version via the details API first; only DOI resolution fans out across biorxiv/medrxiv/both (default both) — the full-text fetch itself targets whichever server answered, named in the output server field
• Long articles page via offset/limit character chunking (default limit 20,000, max 50,000); response reports totalChars, remainingChars, and hasMore, and the extracted article is cached per version so paging costs one origin fetch
• PDF-only preprints and blocked/challenge pages return a typed fulltext_unavailable error routing to biorxiv_get_preprint
• An origin rate limit (HTTP 429) — on either the article-page host or api.biorxiv.org during resolution — returns a retryable rate_limited error carrying the origin's Retry-After wait, with the recovery hint naming which origin is limiting

---

biorxiv_list_categories _tool

• No API call — hardcoded static list (~30 bioRxiv + ~50 medRxiv categories)
• Use to validate category strings before passing to biorxiv_list_recent

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

bioRxiv-specific:

• BiorxivApiService wraps api.biorxiv.org — details, publications, and crosswalk endpoints with retry and exponential backoff; a 429 is classified as a retryable rate_limited error carrying the parsed Retry-After wait, with the upstream response body kept out of the payload
• EuropePmcService wraps the EuropePMC search endpoint for relevance-ranked keyword and/or author results, classified the same way on a 429
• BiorxivFullTextService fetches and extracts Markdown from the rendered HTML article pages on www.biorxiv.org / www.medrxiv.org — a distinct origin from the JSON API
• Two-server fan-out via Promise.allSettled — both biorxiv and medrxiv queried in parallel when server="both", results merged and deduplicated by DOI
• Polite User-Agent header including a mailto address (BIORXIV_MAILTO env var) per Cold Spring Harbor Lab API guidelines
• Pairs with pubmed-mcp-server (post-publication), openalex-mcp-server (citation analytics), and crossref-mcp-server (DOI metadata)

Agent-friendly output:

• Graceful partial failure — per-DOI and per-server failures land in failed[] with a typed reason and retryable flag instead of aborting the whole batch or listing call
• Rate-limit transparency — a 429 from any upstream surfaces as reason: "rate_limited" carrying the origin's parsed retryAfter wait, distinguished from a generic upstream_unavailable
• Discriminated enrichment outputs — biorxiv_search_preprints results carry enriched plus a typed enrichment_error (service_error / rate_limited / not_found) so callers branch on data, not string parsing
• Paging and pagination state — exhausted cursors are flagged as an out-of-range artifact rather than an empty interval, and biorxiv_get_fulltext reports totalChars / remainingChars / hasMore for chunked reads

Getting started

Public Hosted Instance

A public instance is available at https://biorxiv.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "biorxiv-mcp-server": {
      "type": "streamable-http",
      "url": "https://biorxiv.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "biorxiv-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/biorxiv-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "BIORXIV_MAILTO": "[email protected]"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "biorxiv-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/biorxiv-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "BIORXIV_MAILTO": "[email protected]"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "biorxiv-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "-e", "[email protected]", "ghcr.io/cyanheads/biorxiv-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 [email protected] bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/biorxiv-mcp-server.git

2. Navigate into the directory:

cd biorxiv-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# optionally set BIORXIV_MAILTO for polite API access

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts.

Variable	Description	Default
BIORXIV_MAILTO	Email address included in the User-Agent header for polite API access per Cold Spring Harbor Lab guidelines. Optional, but recommended.	—
BIORXIV_API_BASE_URL	Override the bioRxiv API base URL.	https://api.biorxiv.org
EUROPEPMC_API_BASE_URL	Override the EuropePMC base URL.	https://www.ebi.ac.uk/europepmc/webservices/rest
BIORXIV_WEB_BASE_URL	Override the bioRxiv website base URL (full-text HTML source for biorxiv_get_fulltext).	https://www.biorxiv.org
MEDRXIV_WEB_BASE_URL	Override the medRxiv website base URL (full-text HTML source for biorxiv_get_fulltext).	https://www.medrxiv.org
MCP_TRANSPORT_TYPE	Transport: stdio or http.	stdio
MCP_HTTP_PORT	HTTP server port.	3010
MCP_HTTP_ENDPOINT_PATH	HTTP endpoint path.	/mcp
MCP_AUTH_MODE	Auth mode: none, jwt, or oauth.	none
MCP_LOG_LEVEL	Log level (debug, info, warning, error, etc.).	info
LOGS_DIR	Directory for log files (Node.js only).	<project-root>/logs
OTEL_ENABLED	Enable OpenTelemetry instrumentation.	false

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t biorxiv-mcp-server .
docker run --rm -e [email protected] -p 3010:3010 biorxiv-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/biorxiv-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Directory	Purpose
src/index.ts	createApp() entry point — registers tools and initializes services.
src/config	Server-specific environment variable parsing and validation with Zod.
src/mcp-server/tools	Tool definitions (*.tool.ts). Six tools across bioRxiv and medRxiv.
src/services/biorxiv	BiorxivApiService — details, publications, and crosswalk endpoint wrappers with retry.
src/services/biorxiv-fulltext	BiorxivFullTextService — rendered HTML article page fetch and Markdown extraction.
src/services/europe-pmc	EuropePmcService — preprint keyword/author search endpoint wrapper.
tests/	Unit and integration tests mirroring the src/ structure.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Register new tools via the barrel in src/mcp-server/tools/definitions/index.ts
• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.