Awesome Medical MCP Servers
A collection of Medical MCP servers.
What is Awesome Medical MCP Servers?
Awesome Medical MCP Servers is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to collection of medical mcp servers.
A collection of Medical MCP servers.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A collection of Medical MCP servers.
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx awesome-medical-mcp-serversConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Awesome Medical MCP Servers
Awesome Medical MCP Servers is a curated directory of MCP server implementations focused on healthcare and life-sciences use cases, aggregating projects that connect AI assistants to PubMed literature search, FHIR/EMR systems, DICOM medical imaging, drug shortage data, medical calculators, oncology document management, and more. It serves as a starting point for developers and clinicians who want to integrate AI tooling into medical workflows by pointing them at vetted, topic-specific MCP servers rather than building from scratch.
Prerequisites
- An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
- Node.js 18+ or Python 3.10+ depending on which individual server you choose to run
- Relevant API credentials for the specific server (e.g. NCBI/Entrez API key for PubMed servers, FHIR endpoint credentials for EMR integration)
- A running instance of any backend systems required by the chosen server (e.g. a DICOM PACS server, an Epic/Cerner FHIR endpoint)
Browse the directory and choose a server
Visit the repository at https://github.com/sunanhe/awesome-medical-mcp-servers and review the listed servers. Identify which one fits your use case — PubMed search, DICOM imaging, FHIR integration, medical calculations, etc.
Clone or install the chosen server
Navigate to the individual server's repository and follow its own installation instructions. For example, to install the PubMed server by andybrandt:
pip install mcp-simple-pubmed
# or for npm-based servers:
npx -y <server-package-name>Set up required credentials
Each server has its own environment variables. For PubMed-based servers you typically need an NCBI Entrez API key. For FHIR servers you need EMR endpoint URLs and OAuth tokens. Check each server's README for the exact variable names.
export NCBI_API_KEY=your_entrez_api_key
export FHIR_BASE_URL=https://your-emr.example.com/fhirConfigure your MCP client
Add the chosen server to your MCP client's configuration file. The exact command and args differ per server — refer to the individual project's README for the correct invocation.
Test with a medical query
Restart your MCP client and try a prompt relevant to the installed server, such as searching PubMed for recent articles or retrieving a patient's FHIR records.
Awesome Medical MCP Servers Examples
Client configuration (PubMed example)
Example configuration for the mcp-simple-pubmed server, one of the servers listed in the collection.
{
"mcpServers": {
"pubmed": {
"command": "python",
"args": ["-m", "mcp_simple_pubmed"],
"env": {
"NCBI_API_KEY": "your_ncbi_api_key"
}
}
}
}Prompts to try
Representative prompts you can use once you have one of the medical MCP servers connected.
- "Search PubMed for recent randomized controlled trials on GLP-1 receptor agonists."
- "Show me the DICOM study list for patient ID 12345 from our PACS."
- "Calculate the CHA2DS2-VASc score for a 70-year-old patient with hypertension and diabetes."
- "What drugs are currently on the shortage list in Switzerland?"
- "Retrieve the latest NICE guideline for type 2 diabetes management."Troubleshooting Awesome Medical MCP Servers
The chosen server fails to start with a missing module error
Each server in the collection has its own dependencies. Install them per the individual server's README (pip install -r requirements.txt or npm install). The awesome-list repo itself is a directory, not a runnable package.
PubMed searches return a rate-limit error without an API key
NCBI enforces strict rate limits for unauthenticated requests (3/second). Register for a free NCBI API key at https://www.ncbi.nlm.nih.gov/account/ and set it as NCBI_API_KEY in your environment.
FHIR server returns authentication errors
FHIR endpoints typically require OAuth 2.0 bearer tokens. Obtain a token from your EMR's identity provider (Epic, Cerner) and pass it per the FHIR MCP server's documented environment variable (commonly FHIR_ACCESS_TOKEN or similar).
Frequently Asked Questions about Awesome Medical MCP Servers
What is Awesome Medical MCP Servers?
Awesome Medical MCP Servers is a Model Context Protocol (MCP) server that collection of medical mcp servers. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Awesome Medical MCP Servers?
Follow the installation instructions on the Awesome Medical MCP Servers GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Awesome Medical MCP Servers?
Awesome Medical MCP Servers works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Awesome Medical MCP Servers free to use?
Yes, Awesome Medical MCP Servers is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Awesome Medical MCP Servers Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Awesome Medical MCP Servers? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Awesome Medical MCP Servers in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Awesome Medical MCP Servers?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.