This project provides a self-hostable Model Context Protocol (MCP) server that integrates comprehensive Google Maps APIs, enabling AI agents to understand and interact with the physical world. It offers 18 tools for geocoding, routing, place searching, and more, empowering AI with real-world geospatial reasoning capabilities.

How It Works

The server exposes 18 Google Maps functionalities, including 14 atomic tools (e.g., geocoding, directions, weather) and 4 composite tools (e.g., explore-area, plan-route, local-rank-tracker). It leverages Google's Places API (New) and Routes API, built with TypeScript and Node.js. The project offers stdio and StreamableHTTP modes, alongside built-in "Agent Skill" definitions that guide AI on how to chain these geospatial tools effectively.

Quick Start & Requirements

Installation is typically done via npx @cablate/mcp-google-map. Key requirements include a Google Cloud Project with enabled Places API (New) and Routes API, and a valid GOOGLE_MAPS_API_KEY configured via environment variables or command-line arguments. Development requires Node.js and npm.

Highlighted Details

• Features 18 Google Maps tools, including advanced composite tools like explore-area, plan-route, compare-places, and a unique local-rank-tracker for SEO analysis.
• Provides built-in "Agent Skill" definitions to teach AI agents how to effectively chain geospatial tools.
• Offers both stdio and StreamableHTTP server modes for flexible integration.
• Supports batch geocoding up to 50 addresses concurrently.

Maintenance & Community

The project is actively developed, with recent additions including several composite tools and feature filters. Planned features include place photo retrieval and multi-language support. Community contributions are welcomed, with contact via email and GitHub.

Licensing & Compatibility

The project is released under the MIT license, permitting commercial use and integration into closed-source applications. It is designed for self-hosting, offering greater control and flexibility.

Limitations & Caveats

Operation is contingent on obtaining and configuring Google Cloud API keys and enabling specific Google Cloud services. Some advanced features, such as retrieving place photos, are still in the planning stages.