How to Use the Google Maps MCP in Vercel AI SDK

Q: How do I handle Google Maps coordinates inside my Vercel AI SDK stream?

Use createMCPClient to connect this MCP Server, then pass its tools directly into streamText. When the agent calls geocode, your frontend captures the tool call argument and renders a map component using the raw latitude and longitude coordinates immediately.

Q: How do I close the Google Maps connection in Vercel AI SDK?

Always call mcpClient.close() once your streaming generator finishes its execution. This prevents hanging HTTP connections in your serverless environments and keeps your Vercel bill clean.

Q: Can my agent search for nearby spots using this setup?

The placesearch tool handles local queries like coffee shops or gas stations instantly. It returns a list of candidate locations that the agent can immediately process or display.

Feed live Google Maps coordinates and routes directly into your Vercel AI SDK frontend without making users stare at loading spinners.

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 Vercel AI SDK

Create your Vinkius account to connect Google Maps to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render live routes in the UI

The `directions` tool lets your Vercel AI SDK app grab exact route calculations and immediately push them to the client's screen. Instead of waiting for a complete API payload to resolve, the streaming architecture lets you pipe the coordinates straight into your React or Next.js map components. This approach cuts down perceived latency by rendering the path step-by-step. Users see their travel times and distances populate in real-time, making the interface feel twice as fast as traditional REST setups.

Instant UI updates via this MCP Server

The `geocode` tool converts plain text addresses into exact latitude and longitude coordinates that your Vercel AI SDK agent uses to pin locations on a map. By plugging this MCP Server into your streaming runtime, the agent can resolve ambiguous user inputs and update the map UI while the text response is still generating. You avoid writing complex coordinate-parsing logic on your frontend. The server feeds clean coordinate objects directly into your Edge Functions, keeping the payload small and the execution time under 100 milliseconds.

Live venue details for interactive cards

The `place_details` tool retrieves phone numbers, operating hours, and website URLs for any venue, letting your Vercel AI SDK application build rich UI components on the fly. When a user asks about a restaurant, the streaming agent populates custom UI cards with live data before the text generation even finishes. This keeps your frontend clean because you don't have to pre-fetch thousands of local business records. The agent grabs exactly what it needs for the active view, keeping your Edge runtime lightweight and fast.

Setup guide

Set up Google Maps MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Google Maps tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Google Maps transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use `createMCPClient` to connect this MCP Server, then pass its tools directly into `streamText`. When the agent calls `geocode`, your frontend captures the tool call argument and renders a map component using the raw latitude and longitude coordinates immediately.

Yes. This MCP Server is fully compatible with Edge runtimes because it communicates over standard HTTP. Your agent calls `directions` to calculate routes without hitting cold starts or package size limits.

Always call `mcpClient.close()` once your streaming generator finishes its execution. This prevents hanging HTTP connections in your serverless environments and keeps your Vercel bill clean.

The `place_search` tool handles local queries like coffee shops or gas stations instantly. It returns a list of candidate locations that the agent can immediately process or display.

We process raw addresses and coordinates inside an isolated, zero-trust V8 sandbox. No location coordinates or search queries are stored on our servers, and all API calls are encrypted in transit.

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