calculate_routeLABSCO SUMMARY
Your own Maps endpoint, on your own key.
Routing questions cost Google API calls whoever asks them. Running the server yourself keeps the key, the quota and the per-IP limit under your control, and the four tools stay on the practical side of Maps: which way, how long, how much.
What it is
A Node MCP server for Google Maps, packaged for Google Cloud Run and reached over SSE. Four tools covering routing, route comparison, live traffic and trip cost, with rate limiting built in.
What you get
- An optimal driving route calculated against real-time traffic
- Several routing alternatives compared under different options
- Current traffic conditions and travel-time analysis
- Trip cost estimated including fuel and tolls
- Your own deployed service, so the endpoint, the key and the quota stay yours
- Per-IP rate limiting, counted by the hour
Requirements
A GCP account with billing enabled, the gcloud CLI, and Node.js 18+ for local work. Enable the Directions and Geocoding APIs (Maps JavaScript is optional, for polyline encoding), put a Google Maps API key in the environment, then deploy with ./simple-deploy.sh <project-id> <region> and give your client the service URL with /sse on the end. The deployed service takes no authentication of its own — it is public, and rate-limited per IP by the hour.
Setup effort
Follow the published steps — gcloud services enable directions-backend.googleapis.com
USE CASES
01
Choosing between two ways of getting there
Compare the alternatives under the options that matter, then take the route that wins.
02
Deciding whether to leave now or wait
Read current traffic and the travel-time analysis before committing to a departure.
03
Quoting the cost of a journey
Price the trip with fuel and tolls included, against the route actually being driven.
04
Planning a route while traffic is still moving
Recalculate with live conditions rather than the static estimate you started with.
4 tools
Listed in project docs. Your client may show a different list.
compare_routesget_live_trafficestimate_costsBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- npx on PATH
- Node.js 18+
INSTALLATION
Connect your client
Server setup
In a Google Cloud project with billing enabled and the gcloud CLI configured, enable the Directions and Geocoding APIs:
TERMINAL
gcloud services enable directions-backend.googleapis.com
gcloud services enable geocoding-backend.googleapis.comCreate a Google Maps API key at https://console.cloud.google.com/google/maps-apis/credentials and restrict it to those APIs
TERMINAL
git clone https://github.com/arunrajece/google-maps-mcp-cloudrun
cd google-maps-mcp-cloudrun
export GOOGLE_MAPS_API_KEY="<YOUR_GOOGLE_MAPS_API_KEY>"
./simple-deploy.sh <YOUR_GCP_PROJECT_ID> us-central1
gcloud run services describe google-maps-mcp --region us-central1 --format="value(status.url)"Add /sse to the URL that prints: that is https://<YOUR_SERVICE_URL>.run.app/sse in your client
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"google-maps": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://<YOUR_SERVICE_URL>.run.app/sse"
]
}
}
}
