Which integrations are available for this server?

Uses [OpenAI](/mcp/servers/integrations/openai)'s GPT models to translate natural language queries into structured API parameters for ClinicalTrials.gov

MCP Server for ClinicalTrials.gov Natural Language API

This MCP (Model Control Protocol) server allows you to query ClinicalTrials.gov using natural language. It uses OpenAI's GPT models to translate your query into API parameters and returns structured results.

Features

Accepts natural language queries (e.g., "Show me completed phase 3 diabetes trials in Canada")
Uses OpenAI API to parse and map to ClinicalTrials.gov API parameters
Returns both the parsed parameters and the results

Related MCP server: AACT Clinical Trials MCP Server

Requirements

Python 3.8+
Dependencies in requirements.txt
OpenAI API key (set as OPENAI_API_KEY environment variable)

Running the Server

Install dependencies:
pip install -r requirements.txt
Set your OpenAI API key:
export OPENAI_API_KEY=sk-...
Start the server:
uvicorn server:app --reload

Usage

cURL Example

curl -X POST "http://127.0.0.1:8000/query" \ -H "Content-Type: application/json" \ -d '{"query": "Show me completed phase 3 diabetes trials in Canada"}'

Python Example

import requests query = "Show me completed phase 3 diabetes trials in Canada" response = requests.post( "http://127.0.0.1:8000/query", json={"query": query} ) print(response.json())

What is MCP?

MCP (Model Control Protocol) is a pattern for building AI-driven APIs that act as a control layer between natural language and structured APIs. This server uses an LLM to interpret user intent and map it to API calls, making complex data accessible via plain language.