18 Google Maps tools for AI agents — geocode, search, directions, weather, and more.
Model Context Protocol (MCP) Server: io.github.cablate/google-map
This MCP server provides 18 Google Maps tools for AI agents, covering capabilities such as geocode, search, directions, weather, and additional related functions. It is published under the package name path @cablate/mcp-google-map and is described as an MCP server for use with agent skills.
🛠️ Key Features
18 Google Maps tools for AI agents
Tooling includes geocoding, search, directions, and weather
Uses MCP and is associated with Places API concepts
🚀 Use Cases
Agent geocoding and location lookup
Route planning via directions tools
Enrichment using search and weather-related outputs
⚡ Developer Benefits
Designed for Model Context Protocol integration
Relevant topics include geospatial and google-maps development
Includes streamable HTTP and TypeScript in its stated topic set
⚠️ Limitations
Only the existence and scope of “18 tools” is stated; specific tool names, auth, and response formats are not provided in the provided data
# stdio (Claude Desktop, Cursor, etc.)
npx @cablate/mcp-google-map --stdio
# exec CLI — no server needed
npx @cablate/mcp-google-map exec geocode '{"address":"Tokyo Tower"}'# HTTP server
npx @cablate/mcp-google-map --port 3000 --apikey "YOUR_API_KEY"
Special Thanks
Special thanks to @junyinnnn for helping add support for streamablehttp.
Available Tools
Tool
Description
maps_search_nearby
Find places near a location by type (restaurant, cafe, hotel, etc.). Supports filtering by radius, rating, and open status.
maps_search_places
Free-text place search (e.g., "sushi restaurants in Tokyo"). Supports location bias, rating, open-now filters.
maps_place_details
Get full details for a place by its place_id — reviews, phone, website, hours. Optional maxPhotos param returns photo URLs.
maps_geocode
Convert an address or landmark name into GPS coordinates.
maps_reverse_geocode
Convert GPS coordinates into a street address.
maps_distance_matrix
Calculate travel distances and times between multiple origins and destinations. Driving mode supports avoid_tolls and avoid_highways.
maps_directions
Get step-by-step navigation between two points with route details. Driving mode supports avoid_tolls and avoid_highways.
maps_elevation
Get elevation (meters above sea level) for geographic coordinates.
maps_timezone
Get timezone ID, name, UTC/DST offsets, and local time for coordinates.
maps_weather
Get current weather conditions or forecast — temperature, humidity, wind, UV, precipitation.
maps_air_quality
Get air quality index, pollutant concentrations, and health recommendations by demographic group.
maps_static_map
Generate a map image with markers, paths, or routes — returned inline for the user to see directly.
maps_batch_geocode
Geocode up to 50 addresses in one call — returns coordinates for each.
maps_search_along_route
Search for places along a route between two points — ranked by minimal detour time.
Composite Tools
maps_explore_area
Explore what's around a location — searches multiple place types and gets details in one call.
maps_plan_route
Plan an optimized multi-stop route — uses Routes API waypoint optimization (up to 25 stops) for efficient ordering. Driving mode supports avoid_tolls and avoid_highways.
Track a business's local search ranking across a geographic grid — like LocalFalcon. Supports up to 3 keywords for batch scanning. Returns rank at each point, top-3 competitors, and metrics (ARP, ATRP, SoLV).
All tools are annotated with readOnlyHint: true and destructiveHint: false — MCP clients can auto-approve these without user confirmation.
Prerequisite: Enable Places API (New) and Routes API in Google Cloud Console before using place-related and routing tools.
Installation
Method 1: stdio (Recommended for most clients)
Works with Claude Desktop, Cursor, VS Code, and any MCP client that supports stdio:
All 18 tools available: geocode, reverse-geocode, search-nearby, search-places, place-details, directions, distance-matrix, elevation, timezone, weather, air-quality, static-map, batch-geocode-tool, search-along-route, explore-area, plan-route, compare-places, local-rank-tracker. See skills/google-maps/ for the agent skill definition and full parameter docs.
To use the Agent Skill without MCP:
Install the entire skills/google-maps/ folder in your agent's Skills directory, following that client's instructions. Keep SKILL.md and references/ together. Clients that support .skill imports can use the bundled SKILL.skill archive instead. Installing the npm package alone does not register a Skill with an agent.
Make Node.js 18+ and npx available to the agent, and set GOOGLE_MAPS_API_KEY in its environment. Prefer the environment variable to --apikey, which can expose a key in shell history or process listings.
Ask the agent a location question. The Skill guides it to call the standalone CLI, for example npx -y @cablate/mcp-google-map exec geocode '{"address":"Tokyo Tower"}'. No MCP server or MCP client configuration is needed.
You can verify the CLI is available with npx -y @cablate/mcp-google-map exec --help before making a billable API call.
For a reproducible no-MCP walkthrough, see the Agent Skill demo. If your agent or app displays Places reviews, photos, or AI summaries, follow the content attribution and storage guidance; the tool preserves source/disclosure metadata but does not render a compliant UI for you.
# Clone the repository
git clone https://github.com/cablate/mcp-google-map.git
cd mcp-google-map
# Install dependencies
npm install
# Set up environment variablescp .env.example .env# Edit .env with your API key# Build the project
npm run build
# Start the server
npm start
# Or run in development mode
npm run dev
Testing
bash
# Run smoke tests (no API key required for basic tests)
npm test# Run full E2E tests (requires GOOGLE_MAPS_API_KEY)
npm run test:e2e
Per-session API key isolation for multi-tenant deployments
DNS rebinding protection available for production
Input validation using Zod schemas
For enterprise security reviews, see Security Assessment Clarifications — a 23-item checklist covering licensing, data protection, credential management, tool contamination, and AI agent execution environment verification.
Community participation and contributions are welcome! Please read CONTRIBUTING.md for development setup, coding guidelines, and the pull request process.