Connects Claude to Google's Data Commons API, letting you search statistical indicators across topics like demographics, economics, and public health, then pull observation data for specific variables. You get search for discovering what data exists, plus retrieval methods that support different formats and chart configurations. Requires a Google API key. Useful when you need Claude to work with real-world statistical datasets without manually exporting CSVs or wrestling with the Data Commons interface directly. Ships with both HTTP and stdio transports, so you can run it as a persistent service or invoke it per-session.
A Model Context Protocol (MCP) server for accessing Data Commons API data.
pip install -r requirements.txt
pip install -e .
docker build -t datacommons-mcp .
docker run -p 8000:8000 datacommons-mcp
Start the server in HTTP mode:
python -m datacommons_mcp.cli serve http --host 0.0.0.0 --port 8000
Start the server in stdio mode:
python -m datacommons_mcp.cli serve stdio
GOOGLE_API_KEY: Your Google API key for Data Commons accessInstall development dependencies:
pip install -e ".[dev]"
Run tests:
pytest
Format code:
black .
isort .
MIT License
com.mcparmory/google-sheets
domdomegg/google-sheets-mcp
henilcalagiya/google-sheets-mcp
cct15/war-dashboard-data
moooonad/mcp-google-sheets-full
io.github.br0ski777/csv-to-json