Google Maps MCP Server

Streamable HTTP MCP server for Google Maps — search places, get details, and plan routes.

Repository: github.com/iceener/maps-streamable-mcp-server

Author: overment

Use Case

This MCP server is designed for location-aware AI agents running on mobile devices like Apple Watch or iPhone. Your client provides the current position, and the AI can:

• Find nearby places (restaurants, stores, gas stations)
• Get directions with turn-by-turn navigation
• Compare distances to multiple destinations
• Check opening hours and ratings before you arrive

It also pairs well with other MCP tools — for example, combining with a Tesla MCP to set navigation destinations directly in your car.

Notice

This repo works in two ways:

• As a Node/Hono server for local workflows
• As a Cloudflare Worker for remote interactions

Features

• ✅ Places — Search nearby places, restaurants, landmarks by text or type
• ✅ Details — Get hours, ratings, reviews, photos, contact info
• ✅ Routes — Calculate walking, driving, transit directions
• ✅ Distance Matrix — Compare distances to multiple destinations
• ✅ Location-aware — All tools work with your current position
• ✅ Dual Runtime — Node.js/Bun or Cloudflare Workers

Design Principles

• LLM-friendly: Unified tools, not 1:1 API mirrors
• Watch-ready: Designed for AI agents with location context
• Smart defaults: 1km radius, 10 results, walking mode
• Clear feedback: Place IDs visible for follow-up queries

Installation

Prerequisites: Bun, Google Cloud project.

0. Client Setup

Your client needs to be aware of the current time and your current location, as both values will be used for searching and planning.

1. Get Google Maps API Key

1. Go to Google Cloud Console
2. Create a new project (or select existing)
3. Navigate to APIs & Services > Library
4. Enable Places API (New) and Routes API
5. Go to APIs & Services > Credentials
6. Click Create Credentials > API Key
7. (Recommended) Restrict key to Places API and Routes API

2. Local Development

cd google-maps-mcp
bun install
cp .env.example .env

Edit .env:

PORT=3000
AUTH_ENABLED=true
AUTH_STRATEGY=bearer

# Generate with: openssl rand -hex 32
BEARER_TOKEN=your-random-auth-token

# Your Google Maps API key
API_KEY=your-google-maps-api-key

Run:

bun dev
# MCP: http://127.0.0.1:3000/mcp

3. Cloudflare Worker (Deploy)

1. Create KV namespace:

wrangler kv:namespace create TOKENS

2. Update wrangler.toml with your KV namespace ID

3. Set secrets:

# Auth token for clients (generate it using: openssl rand -hex 32). This makes the connection to your MCP not open to everyone, but only to those who have this API key.
wrangler secret put BEARER_TOKEN

# Your Google Maps API key
wrangler secret put API_KEY

4. Deploy:

wrangler deploy

Endpoint: https://<worker-name>.<account>.workers.dev/mcp

Client Configuration

Claude Desktop / Cursor (Local)

{
  "mcpServers": {
    "google-maps": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:3000/mcp", "--transport", "http-only"],
      "env": { "NO_PROXY": "127.0.0.1,localhost" }
    }
  }
}

Claude Desktop / Cursor (Cloudflare Worker)

{
  "mcpServers": {
    "google-maps": {
      "command": "npx",
      "args": ["mcp-remote", "https://your-worker.workers.dev/mcp", "--transport", "http-only"]
    }
  }
}

Alice App

Add as MCP server with:

• URL: https://your-worker.workers.dev/mcp
• Type: streamable-http
• Header: Authorization: Bearer <your-BEARER_TOKEN>

Tools

search_places

Find places by text qu

... View full README on GitHub