Unofficial bioRxiv MCP Server
Provides access to bioRxiv and medRxiv preprints via a unified tool with seven methods, including keyword search, metadata retrieval, and statistics.
README
Unofficial bioRxiv MCP Server
Model Context Protocol (MCP) server for accessing bioRxiv and medRxiv preprint servers (Cold Spring Harbor Laboratory). Provides access to 260,000+ preprints across 27 biological and 51 medical science categories.
Features
- Single unified tool (
biorxiv_info) with 7 methods - No API key required — uses the public bioRxiv API
- Keyword search with client-side filtering over date-range browsing
- Full preprint metadata retrieval by DOI (all versions)
- Published preprint tracking (preprint → journal mapping)
- Funder search by ROR ID (NIH, NSF, Wellcome, etc.)
- Content and usage statistics (submissions, views, downloads)
- Subject category listings for both bioRxiv and medRxiv
Installation
cd biorxiv-mcp-server
npm install
npm run build
Usage
{
"mcpServers": {
"biorxiv-mcp-server": {
"command": "node",
"args": ["/path/to/biorxiv-mcp-server/build/index.js"]
}
}
}
Tool: biorxiv_info
Single unified tool with multiple methods accessed via the method parameter.
Methods
1. search_preprints
Search preprints by keywords. Uses client-side filtering over the bioRxiv date-range API (no native keyword search endpoint). Scans up to 300 results across the date range.
{
"method": "search_preprints",
"query": "CRISPR gene editing",
"server": "biorxiv",
"date_from": "2025-01-01",
"date_to": "2025-12-31",
"category": "genetics",
"limit": 30
}
Returns: doi, title, authors, abstract (500 chars), date, category, version, published status.
2. get_preprint_details
Get complete metadata for a specific preprint by DOI, including all versions.
{
"method": "get_preprint_details",
"doi": "10.1101/2024.01.15.575123",
"server": "biorxiv"
}
Returns: all versions with doi, title, authors, full abstract, date, category, license, published status.
3. get_categories
List all available subject categories for bioRxiv (27) and medRxiv (51).
{
"method": "get_categories"
}
4. search_published_preprints
Find preprints that have been formally published in peer-reviewed journals.
{
"method": "search_published_preprints",
"date_from": "2025-01-01",
"publisher": "10.1038",
"server": "biorxiv",
"limit": 30
}
Common publisher DOI prefixes: 10.1038 (Nature), 10.1126 (Science), 10.1016 (Elsevier), 10.1371 (PLOS), 10.7554 (eLife), 10.1073 (PNAS).
5. search_by_funder
Find preprints by funding organization using ROR IDs. Data available from 2025-04-10 onwards.
{
"method": "search_by_funder",
"funder_ror_id": "021nxhr62",
"server": "biorxiv",
"limit": 30
}
Common ROR IDs: 021nxhr62 (NIH), 01cwqze88 (NSF), 02mhbdp94 (European Commission), 029chgv08 (Wellcome Trust), 05a28rw58 (HHMI), 006wxqw41 (MRC).
6. get_content_statistics
Get submission statistics (new papers, revisions, authors).
{
"method": "get_content_statistics",
"interval": "m"
}
Interval: "m" (monthly) or "y" (yearly).
7. get_usage_statistics
Get engagement statistics (views, downloads).
{
"method": "get_usage_statistics",
"interval": "m",
"server": "biorxiv"
}
Example Queries with Claude
Once configured, you can ask Claude:
- "Search bioRxiv for recent CRISPR preprints"
- "Get details for preprint DOI 10.1101/2024.01.15.575123"
- "What bioRxiv categories are available?"
- "Find preprints published in Nature this month"
- "Show NIH-funded preprints in cancer biology"
- "What are the monthly submission statistics for bioRxiv?"
- "Search medRxiv for COVID-19 vaccine preprints"
Important Notes
- Preprints are NOT peer-reviewed — results should not be cited as established fact
- Keyword search is client-side (bioRxiv API only supports date-range browsing), so narrow date ranges improve relevance
- DOI format:
10.1101/YYYY.MM.DD.NNNNNN(bioRxiv prefix is always10.1101) - Funder data only available from April 10, 2025 onwards
Data Source
- Database: bioRxiv / medRxiv (Cold Spring Harbor Laboratory)
- Preprints: 260,000+ across biology and medicine
- Categories: 27 bioRxiv + 51 medRxiv subject areas
- API: https://api.biorxiv.org/
- Rate limits: No published limits, respectful usage encouraged
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。