AACT Clinical Trials MCP Server
Enables querying clinical trial data from the AACT database (ClinicalTrials.gov) using natural language through tools like list_tables, describe_table, and read_query.
README
AACT Clinical Trials MCP Server
Overview
A Model Context Protocol (MCP) server implementation that provides access to the AACT (Aggregate Analysis of ClinicalTrials.gov) database using the FastMCP framework. This server allows AI assistants to directly query clinical trial data from the ClinicalTrials.gov database.
Features
Tools
-
list_tables- Get an overview of all available tables in the AACT database
- Useful for understanding the database structure before analysis
-
describe_table- Examine the detailed structure of a specific AACT table
- Shows column names and data types
- Example:
{"table_name": "studies"}
-
read_query- Execute a SELECT query on the AACT clinical trials database
- Safely handle SQL queries with validation
- Example:
{"query": "SELECT nct_id, brief_title FROM ctgov.studies LIMIT 5", "max_rows": 50}
Configuration
Database Access
- Create a free account at https://aact.ctti-clinicaltrials.org/users/sign_up
- Set environment variables:
DB_USER: AACT database usernameDB_PASSWORD: AACT database password
Usage with Claude Desktop
Note that you need Claude Desktop and a Claude subscription at the moment.
Add one of the following configurations to the file claude_desktop_config.json. (On macOS, the file is located at /Users/YOUR_USERNAME/Library/Application Support/Claude/claude_desktop_config.json and you will need to create it yourself if it does not exist yet).
Option 1: Using the published package
{
"mcpServers": {
"CTGOV-MCP": {
"command": "uvx",
"args": [
"mcp-server-aact"
],
"env": {
"DB_USER": "USERNAME",
"DB_PASSWORD": "PASSWORD"
}
}
}
}
Option 2: Using Docker
Simply add this configuration to claude_desktop_config.json (no build required):
{
"mcpServers": {
"CTGOV-MCP-DOCKER": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--env", "DB_USER=YOUR_USERNAME",
"--env", "DB_PASSWORD=YOUR_PASSWORD",
"navisbio/mcp-server-aact:latest"
]
}
}
}
Option 3: Running from source (development)
Simply add this configuration to claude_desktop_config.json (no build required):
{
"mcpServers": {
"CTGOV-MCP-DOCKER": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--env", "DB_USER=YOUR_USERNAME",
"--env", "DB_PASSWORD=YOUR_PASSWORD",
"navisbio/mcp-server-aact:latest"
]
}
}
}
Example Prompts
Here are some example prompts to use with this plugin:
- "What are the most common types of interventions in breast cancer clinical trials?"
- "How many phase 3 clinical trials were completed in 2023?"
- "Show me the enrollment statistics for diabetes trials across different countries"
- "What percentage of oncology trials have reported results in the last 5 years?"
Troubleshooting
spawn uvx ENOENT Error
This error has been reported when the system cannot find the uvx command which might happen when uvx is installed in a non-standard location (like ~/.local/bin/).
Potential Solution: Update your configuration with the full path. For example:
{
"mcpServers": {
"CTGOV-MCP": {
"command": "/Users/username/.local/bin/uvx",
"args": [
"mcp-server-aact"
],
"env": {
"DB_USER": "USERNAME",
"DB_PASSWORD": "PASSWORD"
}
}
}
}
Contributing
We welcome contributions! Please:
- Open an issue on GitHub
- Start a discussion
- Email: jonas.walheim@navis-bio.com
Acknowledgements
This project was inspired by and initially based on code from:
Thanks to these awesome projects for showing us the way! 🙌
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.