This MCP server provides AI-powered geospatial tools for geocoding, routing, searching, and reasoning about locations using Google Maps APIs. It supports multiple modes of operation including stdio, StreamableHTTP, and standalone CLI execution.
From the registry: 18 Google Maps tools for AI agents — geocode, search, directions, weather, and more.
Please install the `google-map` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Google Maps API key** — Enable Places API (New) and Routes API in your Google Cloud project and create an API key (https://console.cloud.google.com)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@cablate/mcp-google-map","--stdio"]
- required environment variables:
- `GOOGLE_MAPS_API_KEY`: Google Maps API key (example: `<your-api-key>`)
- optional environment variables:
- `GOOGLE_MAPS_ENABLED_TOOLS`: Comma-separated subset of enabled tools (defaults to all 18) (example: `maps_geocode,maps_directions,maps_search_places`)
Note: Also supports HTTP mode via `--port` and an exec CLI for one-shot calls.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GOOGLE_MAPS_API_KEYrequiredAPI key for accessing Google Maps services.MCP server for searching Airweave collections with natural language queries.