How to Use the TomTom MCP in Vercel AI SDK

Q: How do I check traffic incidents with TomTom using the Vercel AI SDK?

Use gettrafficincidents to define a bounding box. The Vercel AI SDK streams the incident details directly into your component. This means the user sees the list populating in real-time, not waiting for a final page load.

Q: If I use TomTom's autocomplete feature with the Vercel AI SDK, what data is streamed?

The autocompleteplacesearch tool takes partial text and optional bias coordinates. The results stream back predictive location suggestions immediately as the user types, making the input feel native to your application.

Q: Can TomTom's route calculation be streamed with the Vercel AI SDK?

Yes. When you call calculateroute, the agent streams both the travel time summary and the full route polyline data simultaneously into your frontend. This makes the whole process feel snappy and dynamic.

Q: What if I need to find specific Points of Interest with TomTom using Vercel AI SDK?

Use searchpoibycategory. Simply provide a category name and a center coordinate. The agent fetches the rich metadata for those POIs, allowing you to display details like phone numbers or hours immediately.

Build real-time, location-aware applications with TomTom using Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TomTom MCP to Vercel AI SDK

Create your Vinkius account to connect TomTom 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 TomTom with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying live traffic data

When your user asks about congestion, the `get_traffic_incidents` tool runs and streams back real-time details. You don't show a spinner; the incident markers appear instantly in the UI. The agent also handles general speed checks using `get_traffic_flow_segment`. This allows you to give immediate feedback on road quality right as the data flows through your Next.js frontend.

Converting addresses and coordinates

Need an address input? The `fuzzy_geocoding` tool takes a messy street name or partial location string and streams back precise latitude/longitude pairs. This works even if the user misspells part of the city. Conversely, if you only have coordinates, run `reverse_geocoding`. Your agent immediately converts those raw points into human-readable street addresses for display.

Finding nearby services fast

Your client can search for anything using the `search_poi_by_category` tool. Give it a category name, like 'hospital,' and a center coordinate. The results stream back instantly as points of interest near that location. For more structured input, use `structured_geocoding`. This requires explicit components—country code and postal code—and gives you reliable coordinates right away.

Setup guide

Set up TomTom 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 TomTom 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 TomTom 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 TomTom. 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 TomTom 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 TomTom MCP in Vercel AI SDK

Use `get_traffic_incidents` to define a bounding box. The Vercel AI SDK streams the incident details directly into your component. This means the user sees the list populating in real-time, not waiting for a final page load.

The `autocomplete_place_search` tool takes partial text and optional bias coordinates. The results stream back predictive location suggestions immediately as the user types, making the input feel native to your application.

Yes. When you call `calculate_route`, the agent streams both the travel time summary and the full route polyline data simultaneously into your frontend. This makes the whole process feel snappy and dynamic.

Use `search_poi_by_category`. Simply provide a category name and a center coordinate. The agent fetches the rich metadata for those POIs, allowing you to display details like phone numbers or hours immediately.

This server handles geographic coordinates (latitude/longitude), physical addresses, and real-time traffic speed metrics. It manages the raw spatial data needed for routing and POI lookups.

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