MCP 服务器

AACT Clinical Trials MCP Server

Provides AI assistants with direct query access to the AACT (Aggregate Analysis of ClinicalTrials.gov) database, allowing structured retrieval and analysis of clinical trial data.

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"}
append_insight
- Record key findings and insights discovered during analysis
- Helps build an analytical narrative
- Example: {"finding": "Phase 3 oncology trials have increased by 15% over the last 5 years"}

Resources

schema://database
- Returns the database schema as a JSON resource
memo://insights
- Returns a formatted memo of insights collected during the session

Configuration

Required Environment Variables

DB_USER: Your AACT database username
DB_PASSWORD: Your AACT database password

Usage with Semantic Kernel

from semantic_kernel import Kernel
from semantic_kernel.connectors.mcp import MCPStdioPlugin

# Create an AACT Clinical Trials MCP plugin
aact_mcp = MCPStdioPlugin(
    name="aact",
    description="Clinical Trials Database Plugin",
    command="uvx",
    args=["mcp-server-aact"],
    env={
        "DB_USER": "your_aact_username", 
        "DB_PASSWORD": "your_aact_password"
    }
)

# Add to Semantic Kernel
kernel = Kernel()
kernel.add_plugin(aact_mcp)

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?"