DROMA MCP Server

- 🔗 Natural Language Interface: Ask questions about drug-omics associations in plain English
- 📊 Dataset Management: Load and manage DROMA datasets (CCLE, gCSI, etc.) in memory
- 📈 Data Loading & Normalization: Load molecular profiles and treatment response data with automatic z-score normalization
- 🗂️ Multi-Project Support: Seamlessly work with data across multiple research projects
- 💾 Smart Caching: Efficient data caching with metadata tracking for faster access
- 📤 Data Export: Export analysis results to various formats (CSV, Excel, JSON)
- ⚡ Multi-Modal Support: Works with various transport protocols (STDIO, HTTP, SSE)
- 🔄 R Integration: Seamless integration with existing DROMA R packages via rpy2
- 🚄 Performance Optimizations: Memory management, asynchronous processing, and connection pooling
- 🛡️ Robust Error Handling: Comprehensive validation, logging, and graceful error recovery
- 🎛️ Class-Based CLI: Modern, type-safe command-line interface with comprehensive help

- Python 3.10+
- R 4.0+ with DROMA.Set and DROMA.R packages
- DROMA SQLite database

pip install droma-mcp

git clone https://github.com/mugpeng/DROMA_MCP
cd DROMA_MCP
pip install -e .

droma-mcp validate

Export a configuration file for your MCP client:

droma-mcp export-config -o droma-config.json
droma-mcp export-config -o droma-http-config.json --transport streamable-http --port 8000

Add to your MCP client configuration:

{
  "mcpServers": {
    "droma-mcp": {
      "command": "droma-mcp",
      "args": ["run", "--db-path", "path/to/droma.sqlite"]
    }
  }
}

droma-mcp validate

droma-mcp export-config --transport streamable-http --port 8080 -o http-config.json

- DROMA_DB_PATH: Default path to DROMA SQLite database
- R_LIBS: Path to R libraries
- DROMA_MCP_MODULE: Server module to load (all, data_loading, database_query, dataset_management)
- DROMA_MCP_VERBOSE: Enable verbose logging

droma-mcp validate

droma-mcp validate

pip install -e .

droma-mcp test --r-libs /path/to/R/libs

R -e "install.packages('rpy2')"

droma-mcp run --verbose
```

1. Define Pydantic schemas in schema/
2. Implement server functions in server/
3. Register tools with FastMCP decorators
4. Update CLI module loading logic