MCP Catalogs
Home

clintrials-mcp

by plainyogurt21·0·Score 33

MCP server providing structured access to ClinicalTrials.gov data with search, retrieval, and analysis capabilities.

ai-llmhealthdeveloper-tools
0
Forks
1
Open issues
7 mo ago
Last commit
2d ago
Indexed

Overview

The clintrials-mcp server enables LLMs to access and analyze clinical trial data from ClinicalTrials.gov through a comprehensive set of tools. It offers multiple search approaches including by condition, intervention, sponsor, NCT ID, or combined criteria, with options for selective field retrieval to optimize responses. The server also provides analysis tools for examining trial phases, field statistics, and data distributions. It supports various deployment options including AWS Lambda, App Runner, Railway, and Render, with a recommended Cloudflare Worker setup for proxying requests to the Python backend.

Try asking AI

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

you:Medical researchers can quickly find relevant clinical trials by condition, intervention, or sponsor
you:Healthcare professionals can retrieve detailed trial information including eligibility criteria and results
you:Data analysts can examine statistical distributions of trial phases and other parameters across studies
you:What is the free tier for AWS Lambda deployment?
you:Can I run this server locally?

When to choose this

Choose this when you need structured access to clinical trial data for research or medical applications, particularly if you're already working with healthcare APIs or clinical research databases.

When NOT to choose this

Don't choose this if you need real-time clinical trial updates (this server depends on the ClinicalTrials.gov API schedule), or if you require highly specialized medical data beyond what ClinicalTrials.gov provides.

Tools this server exposes

9 tools extracted from the README
  • search_trials_by_acronymsearch_trials_by_acronyms(acronyms, max_studies, fields, exact_match)

    Search clinical trials by study acronym

  • search_trials_by_conditionsearch_trials_by_conditions(conditions, max_studies, fields)

    Search clinical trials by medical condition(s)

  • search_trials_by_interventionsearch_trials_by_interventions(interventions, max_studies, fields)

    Search clinical trials by intervention/treatment

  • search_trials_by_sponsorsearch_trials_by_sponsors(sponsors, max_studies, fields)

    Search clinical trials by sponsor/organization

  • search_trials_by_nct_idssearch_trials_by_nct_ids(nct_ids, fields)

    Retrieve specific clinical trials by NCT ID(s)

  • search_trials_combinedsearch_trials_combined(conditions, interventions, sponsors, terms, nct_ids, max_studies, fields)

    Search clinical trials using multiple criteria

  • get_trial_detailsget_trial_details(nct_id, fields)

    Get comprehensive details for a single clinical trial

  • analyze_trial_phasesanalyze_trial_phases(conditions, interventions, sponsors, max_studies)

    Analyze the distribution of trial phases

  • get_field_statisticsget_field_statistics(field_names, field_types)

    Get statistical information about field values

Comparable tools

clinical-mcphealthcare-mcppubchem-mcpbiomarkers-mcp

Installation

Installation

  1. Install dependencies:
pip install -r requirements.txt
  1. Run the MCP server:
python mcp_server.py

Claude Desktop Configuration

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "clintrials": {
      "command": "python",
      "args": ["mcp_server.py"]
    }
  }
}

Alternative Deployments

The server can be deployed to AWS Lambda, Railway, Render, or run locally with Cloudflare Tunnel.

FAQ

What is the free tier for AWS Lambda deployment?
AWS Lambda offers 1 million requests per month for free, then charges $0.20 per 1 million requests.
Can I run this server locally?
Yes, you can run it locally with `python mcp_server.py` or use Cloudflare Tunnel for local development with a public endpoint.

Compare clintrials-mcp with

GitHub →

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