cyanheads

ClinicalTrials.gov MCP Server

Community cyanheads
Updated

A Model Context Protocol (MCP) Server providing LLM tools for the official ClinicalTrials.gov REST API. Search and retrieve clinical trial data, including study details and more

ClinicalTrials.gov MCP Server

TypeScriptModel Context ProtocolVersionLicenseStatusGitHub

Empower your AI agents with direct access to the official ClinicalTrials.gov database!

An MCP (Model Context Protocol) server providing a robust, developer-friendly interface to the official ClinicalTrials.gov v2 API. Enables LLMs and AI agents to search, retrieve, and analyze clinical study data programmatically.

Built on the cyanheads/mcp-ts-template, this server follows a modular architecture with robust error handling, logging, and security features.

๐Ÿš€ Core Capabilities: ClinicalTrials.gov Tools ๐Ÿ› ๏ธ

This server equips your AI with specialized tools to interact with the ClinicalTrials.gov database:

Tool Name Description Key Features
clinicaltrials_list_studies Searches for clinical studies using a combination of query terms and filters. (See Example) - query: Search by condition, term, location, title, intervention, outcomes, sponsor, or ID.- filter: Refine results by NCT IDs, study status, geographic distance, or advanced Essie expressions.- pagination: Control result sets with pageSize and pageToken.- fields: Specify which data fields to return for efficiency.
clinicaltrials_get_study Retrieves detailed information for a single clinical study by its NCT number. (See Example) - nctId: Fetches a study using its unique identifier (e.g., "NCT03934567").- fields: Select specific fields to retrieve.- markupFormat: Choose between markdown or legacy for formatted content.- Uses ClinicalTrials.gov REST API v2.

Table of Contents

| Overview | Features | Installation |

| Configuration | Project Structure |

| Tools | Resources | Development | License |

Overview

The ClinicalTrials.gov MCP Server acts as a bridge, allowing applications (MCP Clients) that understand the Model Context Protocol (MCP) โ€“ like advanced AI assistants (LLMs), IDE extensions, or custom research tools โ€“ to interact directly and efficiently with the official ClinicalTrials.gov database.

Instead of complex API integration or manual searches, your tools can leverage this server to:

  • Automate clinical research workflows: Search for clinical trials, fetch detailed study metadata, and analyze trial characteristics programmatically.
  • Gain research insights: Access comprehensive trial data including study protocols, eligibility criteria, outcomes, sponsors, and locations without leaving the host application.
  • Integrate clinical trial data into AI-driven research: Enable LLMs to conduct clinical trial reviews, analyze research trends, and support evidence-based decision making.
  • Support regulatory and compliance workflows: Retrieve structured data for regulatory submissions, competitive intelligence, and market research.

Built on the robust mcp-ts-template, this server provides a standardized, secure, and efficient way to expose ClinicalTrials.gov functionality via the MCP standard. It achieves this by integrating with the official ClinicalTrials.gov v2 API, ensuring compliance with rate limits and providing comprehensive error handling.

Developer Note: This repository includes a .clinerules file that serves as a developer cheat sheet for your LLM coding agent with quick reference for the codebase patterns, file locations, and code snippets.

Features

Core Utilities

Leverages the robust utilities provided by the mcp-ts-template:

  • Logging: Structured, configurable logging (file rotation, stdout JSON, MCP notifications) with sensitive data redaction.
  • Error Handling: Centralized error processing, standardized error types (McpError), and automatic logging.
  • Configuration: Environment variable loading (dotenv) with comprehensive validation.
  • Input Validation/Sanitization: Uses zod for schema validation and custom sanitization logic.
  • Request Context: Tracking and correlation of operations via unique request IDs using AsyncLocalStorage.
  • Type Safety: Strong typing enforced by TypeScript and Zod schemas.
  • HTTP Transport: High-performance HTTP server using Hono, featuring session management with garbage collection, CORS, and IP-based rate limiting.
  • Authentication: Robust authentication layer supporting JWT and OAuth 2.1, with fine-grained scope enforcement.
  • Deployment: Multi-stage Dockerfile for creating small, secure production images with native dependency support.

ClinicalTrials.gov Integration

  • Official API Integration: Comprehensive access to ClinicalTrials.gov v2 API endpoints with automatic JSON parsing.
  • Advanced Search Capabilities: Complex query construction with filters for study status, geographic location, conditions, interventions, and sponsors.
  • Full Study Metadata: Retrieve complete trial data including protocols, eligibility criteria, study design, outcomes, sponsors, and contact information.
  • Flexible Field Selection: Choose specific data fields to retrieve for efficient API usage and reduced response sizes.
  • Pagination Support: Handle large result sets with built-in pagination using pageSize and pageToken parameters.
  • Multiple Query Types: Support for condition-based, intervention-based, location-based, and sponsor-based searches.
  • Data Format Options: Choose between markdown and legacy markup formats for study descriptions.
  • Rate Limiting Compliance: Built-in request throttling to comply with ClinicalTrials.gov API guidelines.

Installation

Prerequisites

MCP Client Settings

Add the following to your MCP client's configuration file (e.g., cline_mcp_settings.json). This configuration uses npx to run the server, which will automatically install the package if not already present:

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "command": "npx",
      "args": ["clinicaltrialsgov-mcp-server"],
      "env": {
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

If running manually (not via MCP client for development or testing)

Install via npm

npm install clinicaltrialsgov-mcp-server

Alternatively Install from Source

  1. Clone the repository:

    git clone https://github.com/cyanheads/clinicaltrialsgov-mcp-server.git
    cd clinicaltrialsgov-mcp-server
    
  2. Install dependencies:

    npm install
    
  3. Build the project:

    npm run build
    *or npm run rebuild*
    

Configuration

Environment Variables

Configure the server using environment variables. These environmental variables are set within your MCP client config/settings (e.g. claude_desktop_config.json for Claude Desktop)

Variable Description Default
MCP_TRANSPORT_TYPE Transport mechanism: stdio or http. stdio
MCP_HTTP_PORT Port for the HTTP server (if MCP_TRANSPORT_TYPE=http). 3010
MCP_HTTP_HOST Host address for the HTTP server (if MCP_TRANSPORT_TYPE=http). 127.0.0.1
MCP_ALLOWED_ORIGINS Comma-separated list of allowed origins for CORS (if MCP_TRANSPORT_TYPE=http). (none)
MCP_LOG_LEVEL Logging level (debug, info, notice, warning, error, crit, alert, emerg). debug
LOG_OUTPUT_MODE Logging output mode: file or stdout. file
MCP_AUTH_MODE Authentication mode for HTTP: jwt or oauth. jwt
MCP_AUTH_SECRET_KEY Required for jwt auth. Minimum 32-character secret key for JWT authentication. (none)
CLINICALTRIALS_DATA_PATH Directory for caching ClinicalTrials.gov API data. data/ (in project root)
LOGS_DIR Directory for log file storage (if LOG_OUTPUT_MODE=file). logs/
NODE_ENV Runtime environment (development, production). development

Project Structure

The codebase follows a modular structure within the src/ directory:

src/
โ”œโ”€โ”€ index.ts              # Entry point: Initializes and starts the server
โ”œโ”€โ”€ config/               # Configuration loading (env vars, package info)
โ”‚   โ””โ”€โ”€ index.ts
โ”œโ”€โ”€ mcp-server/           # Core MCP server logic and capability registration
โ”‚   โ”œโ”€โ”€ server.ts         # Server setup, capability registration
โ”‚   โ”œโ”€โ”€ transports/       # Transport handling (stdio, http)
โ”‚   โ”œโ”€โ”€ resources/        # MCP Resource implementations
โ”‚   โ””โ”€โ”€ tools/            # MCP Tool implementations (subdirs per tool)
โ”œโ”€โ”€ services/             # External service integrations
โ”‚   โ””โ”€โ”€ clinical-trials-gov/ # ClinicalTrials.gov API client and parsing
โ”œโ”€โ”€ types-global/         # Shared TypeScript type definitions
โ””โ”€โ”€ utils/                # Common utility functions (logger, error handler, etc.)

For a detailed file tree, run npm run tree or see docs/tree.md.

Tools

The ClinicalTrials.gov MCP Server provides a comprehensive suite of tools for clinical trial research, callable via the Model Context Protocol.

Tool Name Description Key Arguments
clinicaltrials_list_studies Searches for clinical studies using queries, filters, and pagination. query?, filter?, fields?, sort?, pageSize?, pageToken?, countTotal?
clinicaltrials_get_study Fetches detailed information for a single study by NCT number. nctId, markupFormat?, fields?

Note: All tools support comprehensive error handling and return structured JSON responses.

Examples

Comprehensive usage examples are available in the examples/ directory:

  • List Studies
  • Get Study Details

Development

Build and Test

# Build the project (compile TS to JS in dist/ and make executable)
npm run build

# Test the server locally using the MCP inspector tool (stdio transport)
npm run inspector

# Test the server locally using the MCP inspector tool (http transport)
npm run inspector:http

# Clean build artifacts
npm run clean

# Generate a file tree representation for documentation
npm run tree

# Clean build artifacts and then rebuild the project
npm run rebuild

# Format code with Prettier
npm run format

# Start the server using stdio (default)
npm start
# Or explicitly:
npm run start:stdio

# Start the server using HTTP transport
npm run start:http

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Built with the Model Context Protocol

MCP Server ยท Populars

MCP Server ยท New