How to integrate Google Maps MCP with Mastra AI

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Google Maps logo
Mastra AI logo
divider

Introduction

This guide walks you through connecting Google Maps to Mastra AI using the Composio tool router. By the end, you'll have a working Google Maps agent that can find walking directions from your hotel to conference center, show top-rated coffee shops near your location, embed a map of downtown restaurants on your website through natural language commands.

This guide will help you understand how to give your Mastra AI agent real control over a Google Maps account through Composio's Google Maps MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Google Maps with

TL;DR

Here's what you'll learn:
  • Set up your environment so Mastra, OpenAI, and Composio work together
  • Create a Tool Router session in Composio that exposes Google Maps tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Google Maps tool definitions and attach them as a toolset
  • Build a Mastra agent that can reason, call tools, and return structured results
  • Run an interactive CLI where you can chat with your Google Maps agent

What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.

Key features include:

  • MCP Client: Built-in support for Model Context Protocol servers
  • Toolsets: Organize tools into logical groups
  • Step Callbacks: Monitor and debug agent execution
  • OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

What is the Google Maps MCP server, and what's possible with it?

The Google maps MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Maps account. It provides structured and secure access to advanced location, routing, and place data, so your agent can perform actions like finding places, calculating routes, searching nearby locations, and generating map embeds on your behalf.

  • Instant directions and route planning: Let your agent fetch detailed step-by-step directions or calculate optimal routes between addresses, including support for waypoints and various travel modes.
  • Proximity-based place search: Effortlessly search for restaurants, parks, or other place types within a specific area, filtered by your preferences and needs.
  • Distance and travel time calculations: Have your agent determine travel distance and estimated time between multiple origins and destinations, factoring in real-world conditions and transport modes.
  • Text-based place discovery: Ask your agent to locate places using natural language queries like “coffee shops near Central Park” or “best hotels in Tokyo.”
  • Interactive map embedding: Generate embeddable map URLs and HTML code to display custom maps, directions, or street views directly in your apps or websites—no manual coding required.

Supported Tools & Triggers

Tools
Autocomplete Place PredictionsReturns place and query predictions for text input.
Compute Route MatrixCalculates travel distance and duration matrix between multiple origins and destinations using the modern Routes API; supports OAuth2 authentication and various travel modes.
Geocode Address With QueryTool to map addresses to geographic coordinates with query parameter.
Geocode DestinationsTool to perform destination lookup and return detailed destination information including primary place, containing places, sub-destinations, landmarks, entrances, and navigation points.
Reverse Geocode LocationTool to convert geographic coordinates (latitude and longitude) to human-readable addresses using reverse geocoding.
Geocode Place by IDTool to perform geocode lookup using a place identifier to retrieve address and coordinates.
Geocoding APIConvert addresses into geographic coordinates (latitude and longitude) and vice versa (reverse geocoding), or get an address for a Place ID.
Geolocate DeviceTool to determine location based on cell towers and WiFi access points.
Get 2D Map TileTool to retrieve a 2D map tile image at specified coordinates for building custom map visualizations.
Get 3D Tiles RootTool to retrieve the 3D Tiles tileset root configuration for photorealistic 3D map rendering.
Get Place DetailsRetrieves comprehensive details for a place using its resource name (places/{place_id} format).
Get RouteCalculates one or more routes between two specified locations.
Lookup Aerial VideoTool to look up an aerial view video by address or video ID.
Embed Google MapTool to generate an embeddable Google Map URL and HTML iframe code.
Nearby searchSearches for places (e.
Get Place PhotoRetrieves high quality photographic content from the Google Maps Places database.
Render Aerial VideoStarts rendering an aerial view video for a US postal address.
Text SearchSearches for places on Google Maps using a textual query (e.
Create Tiles SessionTool to create a session token required for accessing 2D Tiles and Street View imagery.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Node.js 18 or higher
  • A Composio account with an active API key
  • An OpenAI API key
  • Basic familiarity with TypeScript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key.
  • You need credits or a connected billing setup to use the models.
  • Store the key somewhere safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Google Maps through MCP.

Install dependencies

bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv

Install the required packages.

What's happening:

  • @composio/core is the Composio SDK for creating MCP sessions
  • @mastra/core provides the Agent class
  • @mastra/mcp is Mastra's MCP client
  • @ai-sdk/openai is the model wrapper for OpenAI
  • dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio
  • COMPOSIO_USER_ID tells Composio which user this session belongs to
  • OPENAI_API_KEY lets the Mastra agent call OpenAI models

Import libraries and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey as string,
});
What's happening:
  • dotenv/config auto loads your .env so process.env.* is available
  • openai gives you a Mastra compatible model wrapper
  • Agent is the Mastra agent that will call tools and produce answers
  • MCPClient connects Mastra to your Composio MCP server
  • Composio is used to create a Tool Router session

Create a Tool Router session for Google Maps

typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["google_maps"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Google Maps MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "google_maps" for Google Maps access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to

Configure Mastra MCP client and fetch tools

typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
What's happening:
  • MCPClient takes an id for this client and a list of MCP servers
  • The headers property includes the x-api-key for authentication
  • getTools fetches the tool definitions exposed by the Google Maps toolkit

Create the Mastra agent

typescript
const agent = new Agent({
    name: "google_maps-mastra-agent",
    instructions: "You are an AI agent with Google Maps tools via Composio.",
    model: "openai/gpt-5",
  });
What's happening:
  • Agent is the core Mastra agent
  • name is just an identifier for logging and debugging
  • instructions guide the agent to use tools instead of only answering in natural language
  • model uses openai("gpt-5") to configure the underlying LLM

Set up interactive chat interface

typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\n");

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        google_maps: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    console.log("\nSession ended.");
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Google Maps toolsets
  • maxSteps limits how many tool calls the agent can take in a single run
  • onStepFinish is a hook that prints intermediate steps for debugging

Complete Code

Here's the complete code to get you started with Google Maps and Mastra AI:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({ apiKey: composioAPIKey as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["google_maps"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      google_maps: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "google_maps-mastra-agent",
    instructions: "You are an AI agent with Google Maps tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { google_maps: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();

Conclusion

You've built a Mastra AI agent that can interact with Google Maps through Composio's Tool Router. You can extend this further by:
  • Adding other toolkits like Gmail, Slack, or GitHub
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows

How to build Google Maps MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Google Maps MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Google Maps MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Google Maps MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Google Maps MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Google Maps MCP with Claude Cowork

Codex logo

Codex

Use Google Maps MCP with Codex

Cursor logo

Cursor

Use Google Maps MCP with Cursor

OpenClaw logo

OpenClaw

Use Google Maps MCP with OpenClaw

Hermes logo

Hermes

Use Google Maps MCP with Hermes

CLI logo

CLI

Use Google Maps MCP with CLI

Google ADK logo

Google ADK

Use Google Maps MCP with Google ADK

LangChain logo

LangChain

Use Google Maps MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Google Maps MCP with Vercel AI SDK

LlamaIndex logo

LlamaIndex

Use Google Maps MCP with LlamaIndex

CrewAI logo

CrewAI

Use Google Maps MCP with CrewAI

OpenCode logo

OpenCode

Use Google Maps MCP with OpenCode

VS Code logo

VS Code

Use Google Maps MCP with VS Code

FAQ

What are the differences in Tool Router MCP and Google Maps MCP?

With a standalone Google Maps MCP server, the agents and LLMs can only access a fixed set of Google Maps tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Google Maps and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Mastra AI?

Yes, you can. Mastra AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Google Maps tools.

Can I manage the permissions and scopes for Google Maps while using Tool Router?

Yes, absolutely. You can configure which Google Maps scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Google Maps data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗