medical-mcp
Provides tools for searching academic research and retrieving citation information from Google Scholar.
Provides tools for searching medical literature and retrieving detailed article information from PubMed.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@medical-mcpWhat is the recommended dosage of amoxicillin for adults?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🩺 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.
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
Related MCP server: medical-mcp
Quick Start
Ready to bring medical intelligence into your AI workflow? Install in seconds:
Install in Cursor (Recommended):
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 buildFeatures
💊 Drug Information
search-drugs– Search FDA database by brand or generic nameget-drug-details– Get comprehensive drug info by NDC codesearch-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 articlesget-article-details– Detailed article info by PMIDsearch-google-scholar– Academic research with citationssearch-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 caresearch-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 informationsearch-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 startClaude 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-statstool 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
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityCmaintenanceA Model Context Protocol server providing AI assistants with access to healthcare data tools, including FDA drug information, PubMed research, health topics, clinical trials, and medical terminology lookup.Last updated758125MIT
- AlicenseBqualityDmaintenanceAn MCP server that provides comprehensive medical information by querying multiple authoritative medical APIs including FDA, WHO, PubMed, Google Scholar, and RxNorm.Last updated791187108MIT
- FlicenseBqualityDmaintenanceA comprehensive MCP server that provides access to U.S. FDA public datasets via the openFDA API, enabling querying of drug adverse events, labeling, recalls, approvals, shortages, NDC directory, and medical device regulatory data.Last updated1021
- AlicenseAqualityBmaintenanceAn MCP server that enables AI assistants to query U.S. FDA public datasets, including drug adverse events, labeling, recalls, approvals, shortages, NDC directory, and medical device regulatory information.Last updated10MIT
Related MCP Connectors
Hosted MCP server exposing US hospital procedure cost data to AI assistants
This MCP server provides seamless access to Malaysia's government open data, including datasets, w…
MCP server for medicare-coverage
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/samson-art/medical-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server