MCP Catalogs
Home

clinicaltrialsgov-mcp-server

by cyanheads·71·Score 48

MCP server providing 7 tools for searching, retrieving, and matching clinical trials from ClinicalTrials.gov API.

healthcaredeveloper-toolsai-llm
21
Forks
6
Open issues
this month
Last commit
2d ago
Indexed

Overview

A comprehensive MCP server for accessing ClinicalTrials.gov v2 API functionality. It offers seven distinct tools for searching clinical trials, retrieving detailed study information, fetching study results, matching patients to eligible trials, and exploring field values and definitions. Built with TypeScript and based on the @cyanheads/mcp-ts-core framework, it provides both stdio and Streamable HTTP transport options. The server includes proper error handling, rate limiting, retry mechanisms, and supports authentication for HTTP transport.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Medical researchers can search for relevant clinical trials based on specific conditions or interventions
you:Healthcare providers can match patient demographics and conditions to recruiting trials
you:Data analysts can explore clinical trial landscapes using count and search tools for research insights
you:Is an API key required to use this server?
you:Can I use this server with Claude Desktop?

When to choose this

Choose this server when you need to search clinical trials, match patients to studies, or analyze trial data in AI workflows, especially if you want immediate access without hosting your own instance.

When NOT to choose this

Don't choose this if you need to modify or create clinical trial data (this is read-only only), or if you require highly sensitive healthcare data handling with specific compliance requirements.

Tools this server exposes

7 tools extracted from the README
  • clinicaltrials_search_studies

    Search studies with full-text queries, filters, pagination, sorting, and field selection.

  • clinicaltrials_get_study_record

    Fetch a single study by NCT ID. Returns the full record: protocol, eligibility, outcomes, arms, interventions, contacts, and locations.

  • clinicaltrials_get_study_count

    Get total study count for a query without fetching data. Fast statistics and breakdowns.

  • clinicaltrials_get_field_values

    Discover valid values for API fields (status, phase, study type, etc.) with per-value counts.

  • clinicaltrials_get_field_definitions

    Browse the study data model field tree — piece names, types, nesting. Supports subtree navigation and keyword search.

  • clinicaltrials_get_study_results

    Extract outcomes, adverse events, participant flow, and baseline from completed studies. Optional summary mode reduces ~200KB payloads to ~5KB.

  • clinicaltrials_find_eligible

    Match patient demographics and conditions to eligible recruiting trials.

Comparable tools

medline-mcp-serverhealthcare-mcpepic-mcp

Installation

Installation

Public Hosted Instance

A public instance is available at https://clinicaltrials.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "type": "streamable-http",
      "url": "https://clinicaltrials.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add to your MCP client config (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["clinicaltrialsgov-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio"
      }
    }
  }
}

Prerequisites

  • [Bun v1.3.0](https://bun.sh/) or higher (or Node.js >= 24.0.0)

FAQ

Is an API key required to use this server?
No, the ClinicalTrials.gov API is public and doesn't require authentication or API keys.
Can I use this server with Claude Desktop?
Yes, you can configure it via stdio transport or use the public HTTP endpoint.

Compare clinicaltrialsgov-mcp-server with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.