Aact Clinical Trials MCP Server

🚀 AACT Clinical Trials MCP Server

This is an implementation of a Model Context Protocol (MCP) server based on the FastMCP framework, providing access to the AACT (Aggregate Analysis of ClinicalTrials.gov) database. The server allows AI assistants to directly query clinical trial data from the ClinicalTrials.gov database.

🚀 Quick Start

This MCP server enables AI assistants to directly query clinical trial data from the ClinicalTrials.gov database. Users can utilize various tools provided by the server to access and analyze data.

✨ Features

Tools

• list_tables

  • Obtain an overview of all available tables in the AACT database.
  • Useful for understanding the database structure before analysis.

• describe_table

  • View the detailed structure of a specific AACT table.
  • Displays column names and data types.
  • Example: {"table_name": "studies"}

• read_query

  • Execute a SELECT query on the AACT clinical trials database.
  • Securely handle and validate SQL queries.
  • Example: {"query": "SELECT nct_id, brief_title FROM ctgov.studies LIMIT 5"}

• append_insight

  • Record key insights and findings discovered during the analysis.
  • Helps build an analysis narrative.
  • Example: {"finding": "Over the past five years, Phase 3 oncology trials have increased by 15%"}

Resources

• schema://database

  • Returns a JSON resource of the database schema.

• memo://insights

  • Returns a formatted memo of the insights collected during the session.

📦 Installation

Required Environment Variables

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

💻 Usage Examples

Basic Usage

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 the semantic kernel
kernel = Kernel()
kernel.add_plugin(aact_mcp)

Advanced Usage

Here are some example prompts to use with this plugin:

1. "What are the most common intervention types in breast cancer clinical trials?"
2. "How many Phase 3 clinical trials were completed in 2023?"
3. "Show the enrollment statistics of diabetes trials in different countries."
4. "What percentage of oncology trials have reported results in the past five years?"

🔧 Technical Details

This server is built using the following technologies:

• FastMCP to implement the Model Context Protocol.
• Python psycopg2 for PostgreSQL database connection.
• AACT database as the data source for ClinicalTrials.gov information.

📄 License

This project is licensed under the MIT License.

🤝 Contribution

We welcome contributions! Please:

• Open an issue on GitHub.
• Start a discussion.
• Email: jonas.walheim@navis-bio.com

🙏 Acknowledgments

This project was inspired by and initially based on the code of the following projects:

• SQLite MCP Server
• DuckDB MCP Server
• OpenDataMCP

Thanks to these outstanding projects for guiding our way!