Google Maps MCP server

The Google Maps MCP Server provides tools for working with Google Maps API functionality through the Model Context Protocol. It allows you to access geocoding, place search, directions, distance calculations, and more through a standardized interface.

Available Tools

Geocoding Tools

• maps_geocode: Converts an address to coordinates

  • Input: address (string)
  • Returns: location coordinates, formatted address, and place ID

• maps_reverse_geocode: Converts coordinates to an address

  • Inputs:
    • latitude (number)
    • longitude (number)
  • Returns: formatted address, place ID, and address components

Places Tools

• maps_search_places: Searches for places using a text query

  • Inputs:
    • query (string)
    • location (optional): { latitude: number, longitude: number }
    • radius (optional): number (meters, max 50000)
  • Returns: array of places with names, addresses, and locations

• maps_place_details: Gets detailed information about a place

  • Input: place_id (string)
  • Returns: name, address, contact info, ratings, reviews, and opening hours

Navigation Tools

• maps_distance_matrix: Calculates distances and times between points

  • Inputs:
    • origins (string[])
    • destinations (string[])
    • mode (optional): "driving" | "walking" | "bicycling" | "transit"
  • Returns: distances and durations matrix

• maps_directions: Gets directions between points

  • Inputs:
    • origin (string)
    • destination (string)
    • mode (optional): "driving" | "walking" | "bicycling" | "transit"
  • Returns: route details with steps, distance, and duration

Elevation Tool

• maps_elevation: Gets elevation data for locations
  • Input: locations (array of {latitude, longitude})
  • Returns: elevation data for each point

Installation and Setup

Get an API Key

Before using the Google Maps MCP Server, you need to obtain a Google Maps API key:

1. Follow the instructions at Google Maps Documentation
2. Make note of your API key for the configuration steps below

Configure with Claude Desktop

Add the Google Maps MCP Server to your claude_desktop_config.json file using one of the following methods:

Option 1: Using Docker

{
  "mcpServers": {
    "google-maps": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GOOGLE_MAPS_API_KEY",
        "mcp/google-maps"
      ],
      "env": {
        "GOOGLE_MAPS_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Make sure to replace <YOUR_API_KEY> with your actual Google Maps API key.

Option 2: Using NPX

{
  "mcpServers": {
    "google-maps": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-google-maps"
      ],
      "env": {
        "GOOGLE_MAPS_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Again, replace <YOUR_API_KEY> with your actual Google Maps API key.

Usage Examples

Geocoding an Address

To convert an address to coordinates:

const result = await maps_geocode({
  address: "1600 Amphitheatre Parkway, Mountain View, CA"
});

console.log(result.location); // { latitude: 37.422, longitude: -122.084 }
console.log(result.formatted_address); // "1600 Amphitheatre Pkwy, Mountain View, CA 94043, USA"

Finding Nearby Places

To search for restaurants near a specific location:

const places = await maps_search_places({
  query: "restaurants",
  location: { latitude: 37.422, longitude: -122.084 },
  radius: 2000
});

// Returns array of restaurant data within 2km of the specified location

Getting Directions

To get driving directions between two locations:

const directions = await maps_directions({
  origin: "San Francisco, CA",
  destination: "Palo Alto, CA",
  mode: "driving"
});

// Returns detailed route information with steps, distance and duration

Calculating Distances

To get the distance and travel time between multiple locations:

const matrix = await maps_distance_matrix({
  origins: ["Seattle, WA", "Portland, OR"],
  destinations: ["San Francisco, CA", "Los Angeles, CA"],
  mode: "driving"
});

// Returns a matrix of distances and durations between each origin-destination pair

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.