How to Use the Google Maps MCP in Mastra AI

Q: How do I add Google Maps tools to a Mastra AI agent?

Initialize the client with your server URL, call listTools(), and spread them directly into your agent's MCP configuration array. The framework automatically registers placesearch and directions for use.

Q: Can I require human approval for Google Maps routing in Mastra AI?

Yes. You can set requireToolApproval on the directions tool to prevent the MCP Server from calculating expensive routes until a dispatcher approves the request.

Q: Can I fetch detailed venue information like phone numbers?

The placedetails tool fetches operating hours, website links, and contact numbers using a unique ID. It is ideal for enrichment steps in your lead generation pipelines.

Build resilient local-search workflows with Mastra AI and Google Maps tools that auto-retry if APIs hit rate limits.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Maps MCP to Mastra AI

Create your Vinkius account to connect Google Maps to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google Maps with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient routing workflows

The `directions` tool connects directly to Mastra AI workflows, allowing your agents to handle complex routing steps with built-in retry logic. If the Google API rate limit is reached during a heavy dispatch run, the workflow engine automatically retries with exponential backoff to ensure no coordinates are lost. You can build conditional branches that switch routing strategies based on the output. For example, if the distance exceeds 100 miles, the workflow can trigger an approval step for driver overtime before proceeding.

Automated address validation via Mastra AI

The `geocode` tool acts as the first step in your Mastra AI data-cleaning pipelines, converting messy user-submitted addresses into verified geographic coordinates. The workflow engine lets you map this output directly to downstream steps, like updating a CRM or dispatching a driver using this MCP Server. If the geocoding step fails to find a high-confidence match, you can configure a human-in-the-loop step via `requireToolApproval`. This pauses the execution and alerts an operator to verify the address before the agent proceeds.

Multi-step business discovery

The `place_search` tool lets your Mastra AI agent scan specific geographic regions for target businesses and feed the raw results directly into a processing loop. The agent can take the list of places, filter them by rating, and automatically trigger details lookups for the top candidates. This entire sequence runs within a single, stateful workflow that you can deploy to any cloud with a single command. The system handles state management and execution history automatically, so you don't have to write custom database logging code.

Setup guide

Set up Google Maps MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Google Maps tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "google-maps-mcp-client",
  servers: {
    "google-maps-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Google Maps Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Google Maps tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Google Maps transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google Maps. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google Maps now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google Maps MCP in Mastra AI

Initialize the client with your server URL, call `listTools()`, and spread them directly into your agent's MCP configuration array. The framework automatically registers `place_search` and `directions` for use.

Yes. You can set `requireToolApproval` on the `directions` tool to prevent the MCP Server from calculating expensive routes until a dispatcher approves the request.

The built-in workflow engine catches rate-limiting errors and automatically retries the API call. This keeps your automated MCP operations running smoothly without manual developer intervention.

The `place_details` tool fetches operating hours, website links, and contact numbers using a unique ID. It is ideal for enrichment steps in your lead generation pipelines.

All address strings and GPS coordinates are processed on-the-fly inside ephemeral V8 sandboxes. No database stores your location queries on this MCP Server, and the data is completely wiped the moment the workflow step finishes execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript