Set it up
- 1
Turn on Google Maps in your AI
In Claude: open Settings → Connectors and add Google Maps. In ChatGPT: Settings → Apps & Connectors.
- 2
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Google Maps.
- 3
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“Find 3 highly-rated pizza restaurants within 2 miles of Times Square, New York”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"google-maps": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-google-maps"],
"env": {
"GOOGLE_MAPS_API_KEY": "<your-api-key>"
}
}
}
}Paste into your client's MCP configuration file.
Quick skills
Copy one, paste it to your AI, watch it work.
Places Search
“Find the 5 best-rated sushi restaurants within a mile of the Empire State Building”
Directions & Travel Time
“How long does it take to drive from JFK airport to downtown Manhattan at 5pm on a weekday?”
Geocoding
“Geocode this list of 20 business addresses and return lat/lng for each”
Good to know
- · Google Maps is usage-based with monthly free credit — heavy use incurs real cost
- · API keys must have billing enabled on your Google Cloud project
- · Quotas apply per product (Places, Directions, Geocoding) — each has its own limit
When to use
- ✓ You need location-aware answers (places near a point, directions, travel times)
- ✓ You're building travel or logistics workflows
- ✓ You want to validate or geocode addresses
- ✓ You're integrating maps data into an agent workflow
When not to use
- × You only need a static map image — use the Static Maps API directly
- × You need offline maps — this needs network and API quota
- × You're on a tight free tier — Google Maps billing can escalate
About
Imagine asking your AI: 'Find the 5 best-rated coffee shops near me' or 'What's the driving time from the office to the airport during rush hour?' — and it uses Google Maps to answer. This server connects your AI to Google Maps APIs for places, directions, and geocoding.
The official Google Maps MCP server integrates Google Maps Platform APIs into AI assistants. Geocode addresses, get directions, search for places, calculate distances, and access Street View — all through natural language.
Maintained as an official reference implementation with full Google Maps Platform coverage.
Workflows That Use Google Maps MCP
Recommended recipe
Connect your SaaS and cloud accounts to ClaudeStripe, Cloudflare, Vercel, databases and more — manage real accounts through chat, with the API key staying yours.
Works With
FAQ
What does Google Maps MCP do? +
Imagine asking your AI: 'Find the 5 best-rated coffee shops near me' or 'What's the driving time from the office to the airport during rush hour?' — and it uses Google Maps to answer. This server connects your AI to Google Maps APIs for places, directions, and geocoding.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Google Maps MCP? +
Reach for it when you need to: You need location-aware answers (places near a point, directions, travel times); You're building travel or logistics workflows; You want to validate or geocode addresses; You're integrating maps data into an agent workflow.
When should I avoid Google Maps MCP? +
Skip it when: You only need a static map image — use the Static Maps API directly; You need offline maps — this needs network and API quota; You're on a tight free tier — Google Maps billing can escalate.
How do I install Google Maps MCP? +
In Claude Code, run: claude mcp add google-maps -e GOOGLE_MAPS_API_KEY=<your-key> -- npx -y @modelcontextprotocol/server-google-maps. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.
