Installation¶
pip install rmcp
rmcp start
That’s it! RMCP is now ready to handle statistical analysis requests via Claude Desktop, Claude web, or any MCP client.
🎯 Working examples → | 🔧 Troubleshooting →
Development Installation¶
For development, clone the repository and install with uv:
git clone https://github.com/finite-sample/rmcp.git
cd rmcp
uv sync --group dev
Docker Installation¶
Use the pre-built Docker image for a complete R + Python environment:
docker build -f docker/Dockerfile --target development -t rmcp-dev .
docker run -v $(pwd):/workspace -it rmcp-dev bash
# Inside container:
cd /workspace && pip install -e .
rmcp start
R Dependencies¶
RMCP requires R packages for statistical analysis. The Docker approach includes all R packages. For local installation, R dependencies are managed automatically through the security whitelist system.
Check which tools are available:
rmcp list-capabilities
Verification¶
Verify the installation works:
# Check version
rmcp --version
# List available tools (should show 53 tools)
rmcp list-capabilities
# Start the server
rmcp start