CDM MCP Server

A FastAPI-based service that enables AI assistants to interact with Delta Lake tables stored in MinIO through Spark, implementing the Model Context Protocol (MCP) for natural language data operations.

⚠️ Important Warning:

This service allows arbitrary read-oriented queries to be executed against Delta Lake tables. Query results will be sent to the model host server, unless you are hosting your model locally.

❌ Additionally, this service is NOT approved for deployment to any production environment, including CI, until explicit approval is granted by KBase leadership. Use strictly for local development or evaluation purposes only.

Documentation

For detailed documentation, please refer to the User Guide. The guide covers:

• Quick Start - Bring the local service up and running
• Creating Sample Delta Tables - Set up local test data
• Using the API - Direct API usage examples
• AI Assistant Integration - Configure and use with MCP Host tools
  • MCP Configuration - Create mcp.json
  • MCP Host Setup - Configure MCP Host
  • Example Prompts - Natural language examples

Quick Start

1. Clone the repository:

   git clone https://github.com/kbase/cdm-mcp-server.git
   cd cdm-mcp-server

2. Create required directories:

   mkdir -p cdr/cdm/jupyter/cdm_shared_workspace

3. Create Docker network:

   docker network create cdm-jupyterhub-network

4. Start the services:

   docker-compose up -d --build

5. Access the services:

   • MCP Server: http://localhost:8000/docs
   • MinIO Console: http://localhost:9003
   • Spark Master UI: http://localhost:8090
   • JupyterHub: http://localhost:4043

Testing

# Run tests
pytest

# Run with coverage
pytest --cov=src tests/