mcp-maps
Provides route planning and navigation using Google Directions. It can resolve saved-place aliases, preferred stops, and landmarks into routes and relabel route endpoints back to aliases; transit is used by default.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-mapsget transit directions from home to work"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-maps
Routes and navigation (Google Directions) with saved places, as an MCP server.
Tool | |
| the caller's saved places by alias (Home, work…), preferred stops, travel notes |
| a route between aliases / stops / landmarks; transit by default |
| which client and principal your key acts as |
Addresses never leave the server. Tools see aliases; get_route_details resolves them and
relabels the route endpoints back to the alias.
Places are per principal — a household group id forwarded by a trusted client such as
Jarvis (X-On-Behalf-Of: dom), or a client's own id. A caller with no scope gets no places.
See config/places.example.yaml; convert Jarvis's old file with
mcp-maps import-legacy maps_memory.json --principals dom.
Part of the Jarvis tool servers; built on jarvis-mcp-kit (API keys, rate limits, logs).
Run
cp .env.example .env # GOOGLE_MAPS_API_KEY
cp config/clients.example.yaml config/clients.yaml
cp config/places.example.yaml config/places.yaml # your places (gitignored)
uv run --env-file .env mcp-maps serve # http://localhost:8010/mcp/mapsKubernetes: deploy/kubernetes.yaml (clients and places as Secrets). This server holds
personal data — keep it ClusterIP-only.
Related MCP server: Google Maps MCP Server
Connect
Jarvis:
config/subagents.yamlentry withidentity: group.Claude Code:
claude mcp add --transport http maps https://<host>/mcp/maps --header "Authorization: Bearer jvk_…"(add your client id to a scope'sprincipals).
This server cannot be deployed
Maintenance
Related MCP Connectors
Routing, geocoding, places, matrix and map tools for location-aware AI workflows.
Geocode, reverse-geocode, autocomplete, route and search places.
Plan trips on a map: routed transport, day-by-day itineraries, and a plan you can share.
4 Google Maps endpoints. Pay per call in USDC via x402.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables location-aware AI agents to search for nearby places, get detailed place information including hours and ratings, and calculate routes with turn-by-turn directions using Google Maps APIs.22MIT
- AlicenseNot gradedqualityDmaintenanceIntegrates Google Maps routing and traffic capabilities with Claude AI for advanced route planning, real-time traffic analysis, route comparison, and trip cost estimation including fuel and tolls.55 npmMIT
- AlicenseAqualityBmaintenanceEnables AI assistants to access Google Maps services including places search, details, directions, geocoding, and nearby search through natural language.628 PyPI2MIT
- AlicenseNot gradedqualityBmaintenanceProvides geocoding, place search, directions, distance matrix, and elevation data from Google Maps. Enables natural language queries to locate places, get directions, and retrieve map-related information.13 npmMIT