medical-mcp

作者 JamesANZ

An MCP server that provides comprehensive medical information by querying multiple authoritative medical APIs including FDA, WHO, PubMed, Google Scholar, and RxNorm

108
Stars
32
Forks
TypeScript
语言
2026/8/24
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/JamesANZ/medical-mcp

快速入门

使用 medical-mcp 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

🩺 Medical MCP Server

Bring trusted medical data directly into your AI workflow. A local server for private, free access to FDA, WHO, PubMed, RxNorm, and Google Scholar. No API keys. No data leaks.

An MCP (Model Context Protocol) server that brings authoritative medical information into AI coding environments like Cursor and Claude Desktop.

Trust Score

Why Use Medical MCP?

  • 🔒 Your Data Never Leaves – Runs 100% locally; no tracking, no logs, no cloud

  • 🆓 No API Keys – Works out of the box, zero configuration

  • 🏥 Authoritative Sources – FDA, WHO, PubMed, RxNorm, Google Scholar, AAP, pediatric journals

  • Easy Setup – One-click install in Cursor or simple manual setup

  • 🔬 Comprehensive – Drug info, health stats, medical literature, clinical guidelines, pediatric sources

Quick Start

Ready to bring medical intelligence into your AI workflow? Install in seconds:

Install in Cursor (Recommended):

🔗 Install in Cursor

Or install manually:

npm install -g medical-mcp
# Or from source:
git clone https://github.com/JamesANZ/medical-mcp.git
cd medical-mcp && npm install && npm run build

Features

💊 Drug Information

  • search-drugs – Search FDA database by brand or generic name

  • get-drug-details – Get comprehensive drug info by NDC code

  • search-drug-nomenclature – Standardized drug names via RxNorm

📊 Health Statistics

  • get-health-statistics – WHO Global Health Observatory data (life expectancy, mortality, disease prevalence)

🔬 Medical Literature

  • search-medical-literature – Search 30M+ PubMed articles

  • get-article-details – Detailed article info by PMID

  • search-google-scholar – Academic research with citations

  • search-medical-databases – Multi-database search (PubMed, Scholar, Cochrane, ClinicalTrials.gov)

  • search-medical-journals – Top journals (NEJM, JAMA, Lancet, BMJ, Nature Medicine)

🏥 Clinical Tools

  • search-clinical-guidelines – Practice recommendations from medical organizations

👶 Pediatric Sources

  • search-pediatric-guidelines – AAP guidelines and Bright Futures preventive care

  • search-pediatric-literature – Research from major pediatric journals (Pediatrics, JAMA Pediatrics, etc.)

  • get-child-health-statistics – Pediatric health indicators from WHO (mortality, immunization, nutrition)

  • search-pediatric-drugs – Drugs with pediatric labeling and dosing information

  • search-aap-guidelines – Comprehensive AAP guideline search (Bright Futures + Policy Statements)

📊 Cache Management

  • get-cache-stats – View cache statistics (hit rate, memory usage, entry count)

Installation

Cursor (One-Click)

Click the install link above or use:

cursor://anysphere.cursor-deeplink/mcp/install?name=medical-mcp&config=eyJtZWRpY2FsLW1jcCI6eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1lZGljYWwtbWNwIl19fQ==

Manual Installation

Requirements: Node.js 18+ and npm

# Clone and build
git clone https://github.com/JamesANZ/medical-mcp.git
cd medical-mcp
npm install
npm run build

# Run server
npm start

Claude Desktop

Add to claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "medical-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/medical-mcp/build/index.js"]
    }
  }
}

Restart Claude Desktop after configuration.

Usage Examples

Search for Drug Information

Ask about a medication's uses, dosage, and safety information:

{
  "tool": "search-drugs",
  "arguments": { "query": "Tylenol", "limit": 5 }
}

Get Health Statistics

Retrieve global health indicators like life expectancy or mortality rates:

{
  "tool": "get-health-statistics",
  "arguments": {
    "indicator": "Life expectancy at birth (years)",
    "country": "USA"
  }
}

Search Medical Literature

Find peer-reviewed research articles on any medical topic:

{
  "tool": "search-medical-literature",
  "arguments": { "query": "COVID-19 treatment", "max_results": 10 }
}

Data Sources

Source Coverage Update Frequency

FDA All FDA-approved drugs (US) Real-time

WHO Global health stats (194 countries) Annual

PubMed 30M+ medical citations Daily

RxNorm Standardized drug nomenclature (US) Weekly

Google Scholar Academic papers across disciplines Real-time

AAP Bright Futures guidelines & policy statements Periodic

Pediatric Journals Major pediatric journals (Pediatrics, JAMA Pediatrics, etc.) Daily

Security & Privacy

  • Localhost-only – Server runs locally, no external access

  • No data storage – All queries are real-time, nothing saved

  • Process isolation – Medical data stays on your machine

  • No API keys – No credentials to manage or leak

Use Cases

  • Medical Researchers – Quick literature reviews without paywalls

  • Healthcare Developers – Build prototypes with real medical data

  • Students – Access drug information and research papers

  • Clinicians – Reference tool for drug details and health statistics

  • Pediatricians – AAP guidelines, Bright Futures, pediatric literature, and child health data

Caching

The server includes an in-memory caching layer to improve response times and reduce API calls:

  • Automatic Caching: All API responses are cached with source-specific TTL policies

  • TTL Policies:

  • FDA data: 24 hours

  • PubMed articles: 1 hour

  • WHO statistics: 7 days

  • RxNorm nomenclature: 30 days

  • Clinical guidelines: 7 days

  • Google Scholar: 1 hour

  • Bright Futures: 30 days

  • AAP Policy: 7 days

  • Pediatric journals: 1 hour

  • Child health indicators: 7 days

  • Pediatric drugs: 24 hours

  • Cache Management: Automatic cleanup of expired entries every 5 minutes

  • LRU Eviction: Least recently used entries are evicted when cache exceeds 1000 entries

  • Cache Statistics: Use get-cache-stats tool to view hit rates and memory usage

Configuration (via environment variables):

  • CACHE_ENABLED=true - Enable/disable caching (default: true)

  • CACHE_MAX_SIZE=1000 - Maximum cache entries (default: 1000)

  • CACHE_TTL_FDA=86400 - FDA TTL in seconds (default: 86400)

  • CACHE_TTL_PUBMED=3600 - PubMed TTL in seconds (default: 3600)

  • CACHE_TTL_WHO=604800 - WHO TTL in seconds (default: 604800)

  • CACHE_TTL_RXNORM=2592000 - RxNorm TTL in seconds (default: 2592000)

  • CACHE_CLEANUP_INTERVAL=300000 - Cleanup interval in milliseconds (default: 300000)

Performance: Cached responses typically return in <10ms vs 800-1500ms for API calls. Expected cache hit rate: 60%+ for common queries.

Technical Details

Built with: Node.js, TypeScript, MCP SDK

Dependencies: @modelcontextprotocol/sdk, superagent, puppeteer, zod

Platforms: macOS, Windows, Linux

Note: Google Scholar access uses web scraping with rate limiting. Other sources use official APIs.

Medical Disclaimer

⚠️ Important: This tool provides information from authoritative sources but should not replace professional medical advice, diagnosis, or treatment. Always consult qualified healthcare professionals for medical decisions.

Contributing

If this project helps you, please star it on GitHub!

Contributions welcome! Please open an issue or submit a pull request.

License

MIT License – see LICENSE.md for details.

Support

If you find this project useful, consider supporting it:

⚡ Lightning Network

lnbc1pjhhsqepp5mjgwnvg0z53shm22hfe9us289lnaqkwv8rn2s0rtekg5vvj56xnqdqqcqzzsxqyz5vqsp5gu6vh9hyp94c7t3tkpqrp2r059t4vrw7ps78a4n0a2u52678c7yq9qyyssq7zcferywka50wcy75skjfrdrk930cuyx24rg55cwfuzxs49rc9c53mpz6zug5y2544pt8y9jflnq0ltlha26ed846jh0y7n4gm8jd3qqaautqa

₿ Bitcoin: bc1ptzvr93pn959xq4et6sqzpfnkk2args22ewv5u2th4ps7hshfaqrshe0xtp

Ξ Ethereum/EVM: 0x42ea529282DDE0AA87B42d9E83316eb23FE62c3f

常见问题

What is medical-mcp?

medical-mcp is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by JamesANZ. An MCP server that provides comprehensive medical information by querying multiple authoritative medical APIs including FDA, WHO, PubMed, Google Scholar, and RxNorm. It has 108 GitHub stars.

Is medical-mcp safe to use?

medical-mcp failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.

How do I install medical-mcp?

Clone the repository with "git clone https://github.com/JamesANZ/medical-mcp" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is medical-mcp written in?

medical-mcp is primarily written in TypeScript. It is open-source under JamesANZ on GitHub, so you can review or fork the full source.

Are there alternatives to medical-mcp?

Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh medical-mcp against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

Scrapling

by D4Vinci

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

75,9137,581Python
MCP 服务器
查看详情

TrendRadar

by sansan0

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

61,65224,883Python
MCP 服务器
查看详情

context7

by upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

61,0602,938TypeScript
MCP 服务器
查看详情

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

39,9393,219C
MCP 服务器
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情