Clinical Trials MCP Server
Provides programmatic access to ClinicalTrials.gov API with 18 specialized tools for searching, analyzing, and retrieving detailed information about 400,000+ clinical trials worldwide, including filtering by condition, location, phase, sponsor, eligibility criteria, and outcomes.
README

Clinical Trials MCP Server
A comprehensive Model Context Protocol (MCP) server that provides access to the ClinicalTrials.gov API, enabling researchers, clinicians, and developers to access real-time clinical trial data programmatically.
Developed by bachstudio
š Quick Start with npx (Recommended)
No installation required! Use npx to run the server directly:
{
"mcpServers": {
"clinical-trials": {
"command": "npx",
"args": ["-y", "bach-clinical-trials"]
}
}
}
Save this configuration and restart your MCP client. The npx command will automatically download and run the latest version from npm.
Package URL: https://www.npmjs.com/package/bach-clinical-trials
Overview
The Clinical Trials MCP server exposes the full ClinicalTrials.gov API v2.0.4 functionality through 18 specialized MCP tools, allowing you to search, analyze, and retrieve detailed information about clinical trials worldwide directly from your MCP-enabled environment.
Features
Core Search Tools
- search_studies - General search with comprehensive filters (condition, intervention, location, phase, status, age, sex)
- get_study_details - Detailed study information by NCT ID with complete metadata
- search_by_condition - Condition-focused search with eligibility criteria
- search_by_location - Geographic-based search with distance radius filtering
- search_by_sponsor - Organization and sponsor-based search with sponsor type filtering
- search_by_intervention - Treatment, drug, and intervention-focused search
Specialized Search Tools
- get_recruiting_studies - Currently recruiting trials with active contact information
- search_by_date_range - Temporal search by study start and completion dates
- get_studies_with_results - Completed trials with published results
- search_rare_diseases - Specialized search for rare diseases and orphan conditions
- get_pediatric_studies - Pediatric-specific trials for children and adolescents
- search_international_studies - Multi-country international trials
Advanced Analysis Tools
- get_similar_studies - Find studies similar to a reference NCT ID by condition, sponsor, or phase
- search_by_primary_outcome - Search by primary outcome measures and endpoints
- search_by_eligibility_criteria - Advanced eligibility filtering with inclusion/exclusion keywords
- get_study_timeline - Timeline analysis with current, completed, and upcoming studies
- get_trial_statistics - Aggregate statistics and analytics with grouping capabilities
Data Quality Features
- Real-time data access (updated daily Monday-Friday)
- NCT ID validation with regex patterns
- Comprehensive JSON Schema validation
- Geographic coordinate data for study locations
- Contact information for recruiting studies
- Robust error handling and timeout protection
Installation
Prerequisites
- Node.js 16+ (install from nodejs.org)
- No API key required (ClinicalTrials.gov API is publicly accessible)
Setup Steps
-
Navigate to your MCP directory:
cd ~/Documents/Claude/MCP # or your preferred MCP directory -
The server is already built and configured:
ls clinical-trials-server/ # Should show: build/ src/ package.json tsconfig.json README.md -
Verify build:
cd clinical-trials-server ls build/ # Should show: index.js (executable)
Configuration
Add this to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"clinical-trials": {
"command": "node",
"args": ["path/to/clinical-trials-server/build/index.js"],
"autoApprove": [
"search_studies",
"get_study_details",
"search_by_condition",
"search_by_location",
"get_recruiting_studies",
"search_by_sponsor",
"search_by_intervention",
"get_trial_statistics"
]
}
}
}
Note: Replace path/to/clinical-trials-server with the absolute path to your server directory.
Usage Examples
Search for Cancer Trials
{
"condition": "cancer",
"phase": "PHASE3",
"status": "RECRUITING",
"pageSize": 10
}
Get Detailed Study Information
{
"nctId": "NCT05882279"
}
Find Trials by Location
{
"country": "United States",
"city": "Boston",
"distance": 50,
"pageSize": 5
}
Search for Pediatric Studies
{
"condition": "diabetes",
"ageRange": "CHILD",
"recruitmentStatus": "RECRUITING"
}
Get Recruiting Trials with Contacts
{
"condition": "alzheimer",
"location": "California",
"pageSize": 5
}
Find Similar Studies
{
"nctId": "NCT12345678",
"similarityType": "CONDITION",
"pageSize": 10
}
Advanced Eligibility Search
{
"minAge": "18 Years",
"maxAge": "65 Years",
"sex": "ALL",
"healthyVolunteers": false,
"condition": "hypertension",
"inclusionKeywords": "medication",
"exclusionKeywords": "pregnant"
}
Get Trial Statistics
{
"groupBy": "phase",
"filters": {
"condition": "diabetes",
"status": "RECRUITING"
}
}
API Reference
Search Parameters
Common Parameters:
pageSize- Number of results (1-100, default: 10)condition- Medical condition or diseasephase- Study phase: PHASE1, PHASE2, PHASE3, PHASE4, NAstatus- Recruitment status: RECRUITING, NOT_YET_RECRUITING, COMPLETED, etc.
Location Parameters:
country- Country namestate- State or provincecity- City namedistance- Search radius in miles (1-500)
Eligibility Parameters:
sex- ALL, FEMALE, MALEage- CHILD, ADULT, OLDER_ADULTminAge/maxAge- Age ranges (e.g., "18 Years", "65 Years")healthyVolunteers- Boolean for healthy volunteer acceptance
Date Parameters:
startDateFrom/startDateTo- Study start date range (YYYY-MM-DD)completionDateFrom/completionDateTo- Completion date range (YYYY-MM-DD)
Response Format
All tools return structured JSON data including:
- Study metadata (NCT ID, title, status, phase, sponsor)
- Location information with geographic coordinates
- Eligibility criteria and contact information
- Timeline data and key dates
- Comprehensive search criteria documentation
NCT ID Format
All NCT IDs must follow the pattern: NCT######## (NCT followed by 8 digits)
Error Handling
The server includes comprehensive error handling for:
- Network Issues: 30-second timeout protection with retry logic
- Invalid Parameters: JSON Schema validation with descriptive error messages
- API Errors: Proper HTTP status code handling and error reporting
- Missing Data: Graceful handling of optional fields and missing information
- Rate Limiting: Built-in request throttling and error recovery
Common error responses include:
{
"error": "Clinical Trials API error: Invalid NCT ID format",
"isError": true
}
Development
Building from Source
# Install dependencies
npm install
# Build TypeScript to JavaScript
npm run build
# Development with watch mode
npm run watch
Project Structure
clinical-trials-server/
āāā src/
ā āāā index.ts # Main server implementation (all tools)
āāā build/
ā āāā index.js # Compiled executable
āāā package.json # Dependencies and scripts
āāā tsconfig.json # TypeScript configuration
āāā README.md # This file
Key Dependencies
@modelcontextprotocol/sdk- MCP server frameworkaxios- HTTP client for API requests- TypeScript for type safety and development
Data Sources
API Endpoint: https://clinicaltrials.gov/api/v2 Data Updates: Monday through Friday (excluding federal holidays) Coverage: 400,000+ studies from 220+ countries Data Quality: Official FDA/NIH registry with verified information
Troubleshooting
-
Server Connection Issues:
# Test server manually cd clinical-trials-server node build/index.js # Should show: "Clinical Trials MCP server running on stdio" -
Invalid NCT ID Errors:
- Ensure NCT IDs follow format: NCT########
- Example: NCT05882279 ā, nct123 ā
-
No Results Returned:
- Check search criteria - try broader terms
- Some filters may be too restrictive
- Verify spelling of conditions and interventions
-
Timeout Issues:
- Server has 30-second timeout protection
- Large result sets may take time to process
- Reduce pageSize for faster responses
Clinical Research Use Cases
- Patient Recruitment: Find actively recruiting trials for specific conditions
- Competitive Analysis: Research similar studies by sponsors or interventions
- Site Selection: Identify optimal locations for new studies
- Regulatory Research: Access FDA-approved study protocols and outcomes
- Academic Research: Analyze clinical trial trends and statistics
- Patient Care: Help patients find appropriate treatment options
Compliance & Ethics
This server provides access to publicly available clinical trial data from ClinicalTrials.gov. Users should:
- Follow institutional policies for clinical research
- Respect patient privacy and confidentiality
- Use data for legitimate research and healthcare purposes
- Cite ClinicalTrials.gov as the data source in publications
License
MIT License - See LICENSE file for details
Data Source: ClinicalTrials.gov (https://clinicaltrials.gov) API Documentation: https://clinicaltrials.gov/data-api/api Server Version: 1.0.0 Repository: https://github.com/BACH-AI-Tools/ClinicalTrials-MCP-Server
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.