https://github.com/cyanheads/biorxiv-mcp-server
Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP. STDIO or Streamable HTTP.
https://github.com/cyanheads/biorxiv-mcp-server
ai-agent biomedical biorxiv bun cyanheads doi europepmc life-sciences mcp mcp-server medrxiv model-context-protocol preprint research typescript
Last synced: about 1 month ago
JSON representation
Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP. STDIO or Streamable HTTP.
- Host: GitHub
- URL: https://github.com/cyanheads/biorxiv-mcp-server
- Owner: cyanheads
- License: other
- Created: 2026-05-22T03:20:50.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-06-12T07:27:15.000Z (about 2 months ago)
- Last Synced: 2026-06-12T09:17:40.610Z (about 2 months ago)
- Topics: ai-agent, biomedical, biorxiv, bun, cyanheads, doi, europepmc, life-sciences, mcp, mcp-server, medrxiv, model-context-protocol, preprint, research, typescript
- Language: TypeScript
- Homepage: https://www.npmjs.com/package/@cyanheads/biorxiv-mcp-server
- Size: 1.02 MB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
- Citation: CITATION.cff
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-healthcare-mcp-servers - bioRxiv MCP - bioRxiv and medRxiv preprint search, recent listings, and published-version crosswalks (`L2` `B` `TypeScript`). (Life Sciences and Research / Clinical Validity Score)
README
@cyanheads/biorxiv-mcp-server
Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP. STDIO or Streamable HTTP.
5 Tools
[](./CHANGELOG.md) [](./LICENSE) [](https://github.com/users/cyanheads/packages/container/package/biorxiv-mcp-server) [](https://modelcontextprotocol.io/) [](https://www.npmjs.com/package/@cyanheads/biorxiv-mcp-server) [](https://www.typescriptlang.org/) [](https://bun.sh/)
[](https://github.com/cyanheads/biorxiv-mcp-server/releases/latest/download/biorxiv-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=biorxiv-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvYmlvcnhpdi1tY3Atc2VydmVyIl19) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22biorxiv-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads/biorxiv-mcp-server%22%5D%7D)
[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)
---
## Tools
Five tools for working with bioRxiv and medRxiv preprint data:
| 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 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_list_categories` | List valid subject category strings for bioRxiv and medRxiv |
### `biorxiv_get_preprint`
Fetch preprint metadata by DOI — all revisions in one call.
- Batch fetch up to 10 DOIs in a single request
- Each DOI returns the full revision history in `collection[]` — one API call per DOI, no enumeration loop
- Includes title, authors, abstract, category, license, PDF link (`jatsxml`), and published journal DOI when the preprint has been accepted
- Scope to `biorxiv`, `medrxiv`, or `both`; when `both`, each DOI fans out in parallel and partial failures report per-DOI in `failed[]`
---
### `biorxiv_list_recent`
Page through preprints in a date interval.
- Server-side category filtering via `?category=…` — pass a value from `biorxiv_list_categories`
- Fixed page size of 30 (API constraint); advance with integer `cursor` (0, 30, 60, …)
- Response includes `total` count per server for calculating remaining pages
- When `server="both"`, each server paginates independently; response surfaces per-server pagination state (`{ biorxiv: { cursor, total }, medrxiv: { cursor, total } }`)
---
### `biorxiv_search_preprints`
Keyword search with relevance ranking.
- EuropePMC powers relevance ranking (indexes new preprints within 1–2 days of posting); bioRxiv/medRxiv API provides canonical metadata enrichment
- Covers both servers by default; scope down with `server`
- Optional date range filters (`date_from`, `date_to`)
- Enrichment failures degrade gracefully to EuropePMC-only metadata, surfaced via `partial_results`
---
### `biorxiv_get_published_version`
Resolve a preprint DOI to its journal publication crosswalk.
- Uses the `/pubs/{server}/{doi}` endpoint for richer metadata than the `published` field in `biorxiv_get_preprint`
- Returns journal DOI, journal name, published date, and corresponding author institution
- Use when the preprint's `published` field is non-null and you need the full crosswalk record
---
### `biorxiv_list_categories`
Return the static subject category taxonomy for both servers.
- 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`](https://www.npmjs.com/package/@cyanheads/mcp-ts-core):
- Declarative tool definitions — single file per tool, framework handles registration and validation
- Unified error handling across all tools
- Pluggable auth (`none`, `jwt`, `oauth`)
- Swappable storage backends: `in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`
- Structured logging with optional OpenTelemetry tracing
- STDIO and Streamable HTTP transports
bioRxiv-specific:
- `BiorxivApiService` wraps `api.biorxiv.org` — details, publications, and crosswalk endpoints with retry and exponential backoff
- `EuropePmcService` wraps the EuropePMC search endpoint for relevance-ranked keyword results
- 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)
## Getting started
Add the following to your MCP client configuration file.
```json
{
"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": "your@email.com"
}
}
}
}
```
Or with npx (no Bun required):
```json
{
"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": "your@email.com"
}
}
}
}
```
Or with Docker:
```json
{
"mcpServers": {
"biorxiv-mcp-server": {
"type": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "-e", "BIORXIV_MAILTO=your@email.com", "ghcr.io/cyanheads/biorxiv-mcp-server:latest"]
}
}
}
```
For Streamable HTTP, set the transport and start the server:
```sh
MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 BIORXIV_MAILTO=your@email.com bun run start:http
# Server listens at http://localhost:3010/mcp
```
### Prerequisites
- [Bun v1.3.2](https://bun.sh/) or higher (or Node.js v24+).
### Installation
1. **Clone the repository:**
```sh
git clone https://github.com/cyanheads/biorxiv-mcp-server.git
```
2. **Navigate into the directory:**
```sh
cd biorxiv-mcp-server
```
3. **Install dependencies:**
```sh
bun install
```
4. **Configure environment:**
```sh
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` |
| `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). | `/logs` |
| `OTEL_ENABLED` | Enable OpenTelemetry instrumentation. | `false` |
## Running the server
### Local development
- **Build and run:**
```sh
# One-time build
bun run rebuild
# Run the built server
bun run start:stdio
# or
bun run start:http
```
- **Run checks and tests:**
```sh
bun run devcheck # Lint, format, typecheck, security
bun run test # Vitest test suite
bun run lint:mcp # Validate MCP definitions against spec
```
### Docker
```sh
docker build -t biorxiv-mcp-server .
docker run --rm -e BIORXIV_MAILTO=your@email.com -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`). Five tools across bioRxiv and medRxiv. |
| `src/services/biorxiv` | `BiorxivApiService` — details, publications, and crosswalk endpoint wrappers with retry. |
| `src/services/europe-pmc` | `EuropePmcService` — preprint keyword search endpoint wrapper. |
| `tests/` | Unit and integration tests mirroring the `src/` structure. |
## Development guide
See [`CLAUDE.md`](./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 and pull requests are welcome. Run checks and tests before submitting:
```sh
bun run devcheck
bun run test
```
## License
Apache-2.0 — see [LICENSE](./LICENSE) for details.