Medical Research

Unified MCP server that combines ClinicalTrials.gov, PubMed, and FDA data for AI-enhanced analysis

typescript

6

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ezhou89-medical-research-mcp-suite": {
      "command": "node",
      "args": [
        "/Users/eugenezhou/Code/medical-research-mcp-suite/dist/index.js"
      ],
      "env": {
        "FDA_API_KEY": "YOUR_FDA_API_KEY",
        "PUBMED_API_KEY": "YOUR_PUBMED_API_KEY"
      }
    }
  }
}

You can access AI-enhanced medical research data from ClinicalTrials.gov, PubMed, and FDA databases through a unified MCP server. It delivers cross-database insights, risk assessments, and strategic guidance to speed up literature reviews, trial searches, and safety analyses for drug development and clinical research.

How to use

You interact with the MCP server using a client that supports MCP endpoints. Start with the local stdio server configuration to run the MCP locally, then connect your client to the server via the provided command. You can perform comprehensive analyses that combine trial data, literature, and FDA safety information to obtain risk scores, market intelligence, and strategic recommendations.

How to install

Prerequisites: install Node.js 18 or newer and a package manager such as npm or yarn.

Step 1: Clone the project repository.

Step 2: Install dependencies.

Step 3: Build the project.

Additional setup and usage notes

Environment variables shown for running the MCP server include API keys for PubMed and FDA data sources. You can provide these keys to enable API access while respecting rate limits.

Local runtime configuration for the MCP server is provided as part of the Claude Desktop Integration flow. The server runs as a standard Node process and is started with the node runtime pointing to the compiled entry file.

Example environment and startup configuration is shown below. Use this to run the local server and provide your API keys.

To run the local MCP server, use the following command and configuration.

Configuration examples

{
  "mcpServers": {
    "medical_research": {
      "command": "node",
      "args": ["/path/to/medical-research-mcp-suite/dist/index.js"]
    }
  }
}

Security and reliability notes

The MCP server supports intelligent caching, rate limiting, and full audit logging to help you monitor usage and protect data access. Ensure you provide API keys securely and rotate them according to your security policy.

Available tools

ct_search_trials

Enhanced clinical trial search across multiple databases with advanced filters and faceting.

ct_get_study

Retrieve detailed information for a specific clinical study by NCT ID.

pm_search_papers

PubMed literature discovery and query capabilities for papers and abstracts.

fda_search_drugs

Search FDA drug database for product details and safety data.

fda_adverse_events

Analyze adverse events and safety signals from FDA sources.

research_comprehensive_analysis

Cross-database strategic analysis combining trials, literature, and FDA data for risk, market, and strategic insights.

research_drug_safety_profile

Safety analysis across all sources to generate comprehensive drug safety profiles.

research_competitive_landscape

Market intelligence and pipeline analysis across multiple data sources.