mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
claude mcp add --transport stdio cablate-mcp-google-map npx -y @cablate/mcp-google-map \ --env MCP_SERVER_PORT="3000" \ --env GOOGLE_MAPS_API_KEY="YOUR_GOOGLE_MAPS_API_KEY"
How to use
This MCP server provides a Google Maps integration for the MCP protocol with streamable HTTP transport. It exposes a suite of Google Maps tools (including search_nearby, get_place_details, maps_geocode, maps_reverse_geocode, maps_distance_matrix, maps_directions, and maps_elevation) that can be consumed by MCP-enabled clients and LLMs. The server runs over HTTP and supports stateful sessions, multiple concurrent connections, and an echo testing tool to verify MCP interactions. To use it, install the package globally (npm install -g @cablate/mcp-google-map) or run it via npx, then configure your MCP client to connect to the provided HTTP endpoint (default /mcp) and provide your Google Maps API key as needed. Ensure you enable the Places API in your Google Cloud Console if you plan to use Place-related features.
Once running, you can query the server using the MCP protocol by targeting the /mcp endpoint over HTTP. The server will handle the streaming MCP payloads and route them to the appropriate Google Maps tools on demand. Tools available include search_nearby for discovering places near a location, maps_geocode and maps_reverse_geocode for geospatial conversions, distance matrices and directions for routing information, and elevation data for altitude queries. API keys are managed server-side for security.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- Internet access to install packages
Installation options:
Option A: Global installation (recommended)
- Install the MCP Google Map package globally:
npm install -g @cablate/mcp-google-map
- Run the server:
mcp-google-map --port 3000 --apikey "your_api_key_here"
- Optional short form:
mcp-google-map -p 3000 -k "your_api_key_here"
Option B: Use npx (quick start)
- Start the HTTP server in a terminal:
# Run in a separate terminal
npx @cablate/mcp-google-map --port 3000 --apikey "YOUR_API_KEY"
- If you prefer, you can set the API key via environment variable and run without the --apikey flag:
GOOGLE_MAPS_API_KEY=YOUR_API_KEY npx @cablate/mcp-google-map
Configure MCP client to use HTTP transport (not stdio) and point to http://localhost:3000/mcp as the endpoint.
Prerequisites recap:
- Access to a valid Google Maps API key with Maps and Places permissions
- Node.js and npm
- Optional: MCP client that supports streamable HTTP transport
Additional notes
Tips and common considerations:
- Transport: This server uses HTTP transport (not stdio). Do not attempt to run it in stdio mode via MCP server settings.
- API keys: Prefer HTTP headers for API key transmission if your MCP client supports it, otherwise use environment variables or command-line options as shown in the README.
- Places API: If you plan to use new Places-based features, ensure the Places API is enabled in the Google Cloud Console before use.
- Security: API keys are handled server-side; monitor usage and restrict API key permissions and referrers as needed.
- Environment variables: You can configure GOOGLE_MAPS_API_KEY and MCP_SERVER_PORT in a .env file or via the process environment.
- Tools coverage: The server exposes 8 Google Maps tools including search_nearby, get_place_details, maps_geocode, maps_reverse_geocode, maps_distance_matrix, maps_directions, and maps_elevation, plus a built-in Echo service for testing MCP interactions.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
movie-context-provider
An OpenAI App demo built with the OpenAI Apps SDK, that's ready to deploy on Render.
ordiscan
An MCP server for getting information about Ordinals and Runes on Bitcoin