How to integrate Tomtom MCP with Vercel AI SDK v6

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

30 min · no commitment · see it on your stack

Tomtom logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Tomtom to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Tomtom agent that can find nearby ev charging stations with live status, calculate fastest driving route to airport, search for italian restaurants around times square through natural language commands.

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

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

Also integrate Tomtom with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Tomtom integration
  • Using Composio's Tool Router to dynamically load and access Tomtom tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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

The Tomtom MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Tomtom account. It provides structured and secure access to TomTom's advanced mapping, navigation, and location services, so your agent can perform actions like calculating routes, searching for points of interest, retrieving live traffic data, and managing map assets on your behalf.

  • Dynamic route calculation and navigation: Ask your agent to generate driving, walking, or cycling routes with waypoints and real-time traffic considerations to optimize travel plans.
  • Flexible location and place search: Let your agent perform fuzzy searches for addresses or points of interest, or find nearby locations by category such as restaurants, EV charging stations, or landmarks.
  • Real-time traffic flow and road insights: Retrieve up-to-date traffic flow data for specific road segments, helping you monitor congestion, speed trends, and plan detours proactively.
  • EV charging station availability: Check the current status and availability of EV charging stations, making it easy to plan electric vehicle journeys with confidence.
  • Map styling and asset management: Manage map fonts, styles, sprites, and copyrights to customize the look and feel of maps integrated into your applications.

Supported Tools & Triggers

Tools
List Map FontsTool to list available font asset versions for map rendering.
List Assets SpritesTool to list available sprites for a given asset version.
List map stylesTool to list available map styles.
Calculate Long Distance EV RouteTool to calculate long-distance electric vehicle routes with optimal charging stops.
Calculate Matrix Routing SyncTool to calculate route matrix synchronously for multiple origins and destinations (up to 200 cells).
Calculate Reachable RangeTool to calculate the reachable range from a starting point given time, fuel, or energy constraints.
Calculate RouteTool to calculate driving routes.
Calculate Route with BodyTool to calculate routes with advanced options via POST request.
Category SearchTool to search for Points of Interest by category.
Create Notifications Contact GroupTool to create a contact group for TomTom notifications.
Create Routing BatchTool to submit asynchronous batch routing requests to TomTom API.
Create Routing Batch SyncTool to execute synchronous batch routing requests for multiple routes or reachable ranges.
Create Routing Matrix AsyncTool to submit asynchronous matrix routing calculation between multiple origins and destinations.
Create Waypoint OptimizationTool to optimize the sequence of waypoints to find the fastest route.
Geometry FilterTool to filter POIs by geometric boundaries (circles or polygons).
Create Snap to RoadsTool to snap GPS track points to the road network, correcting for GPS inaccuracies.
Create Snap to Roads BatchTool to submit asynchronous batch snap to roads requests to TomTom API.
Delete Notifications HistoryTool to clear the entire notifications history for the account.
Download Batch Search ResultsTool to download results of an asynchronous batch search job.
Download Matrix Routing Async ResultTool to download results of asynchronous matrix routing job.
Download Snap to Roads Async ResultTool to download results of asynchronous snap to roads batch job.
EV Charging Stations AvailabilityTool to retrieve EV charging station availability info.
Flow Segment DataTool to retrieve traffic flow data for a specific road segment.
Fuzzy SearchTool to perform a fuzzy search for addresses and points of interest.
Geocode QueryTool to convert a free-form address query into geographic coordinates.
Get Autocomplete SuggestionsTool to get search suggestions as user types a query.
Get Map Tile CopyrightsTool to retrieve copyright information for TomTom map tiles.
Get Geometry SearchTool to search for POIs and locations within specified geometric areas (circles or polygons).
Get Hillshade TileTool to retrieve hillshade terrain map tiles for specified coordinates and zoom.
Get Incident ViewportTool to retrieve incident viewport information including Traffic Model ID.
Get Map Copyrights Bounding BoxTool to retrieve copyright information for a geographic bounding box.
Get Map Copyrights CaptionTool to retrieve the copyright caption text for TomTom maps.
Get Map Copyrights (Global)Tool to retrieve copyright information for the whole world in the Maps API Raster Tile Service.
Get Orbis Map TileTool to retrieve Orbis map tiles at specified zoom level and coordinates.
Get Orbis Traffic Incident TileTool to retrieve Orbis Traffic Incident Tiles containing traffic incident data in Protocol Buffer format.
Get Map Style MetadataTool to retrieve map style metadata.
Get map styles metadataTool to retrieve map style metadata as a Mapbox Style Specification JSON.
Get Contact GroupTool to retrieve details of a specific contact group by its UUID.
Get Notifications HistoryTool to retrieve notifications history from TomTom.
Get Notifications SettingsTool to retrieve current notification settings.
Orbis GeocodeTool to geocode addresses using TomTom's Orbis Maps API.
Orbis Places AutocompleteTool to get autocomplete suggestions for place searches using TomTom Orbis Maps.
Orbis Structured GeocodeTool to convert structured address fields into geographic coordinates using TomTom Orbis Maps API.
Get Orbis Traffic Flow TileTool to retrieve Orbis traffic flow tile data in Protocol Buffer format.
Get Orbis Traffic Incident DetailsTool to retrieve detailed Orbis traffic incidents by bounding box or IDs.
Get Routing Batch ResultsTool to download asynchronous batch routing results.
Get Matrix Routing Async StatusTool to check the status of an asynchronous matrix routing job.
Get Satellite TileTool to retrieve satellite imagery map tiles at specified coordinates and zoom.
Get Snap to Roads Batch StatusTool to check the status of an asynchronous Snap to Roads batch job.
Get Traffic Flow Tiles RasterTool to retrieve raster traffic flow map tiles for visualization.
Get Traffic Incident DetailsTool to retrieve traffic incident details within a bounding box at a specified zoom level.
Get Traffic Incident TileTool to retrieve raster traffic incident map tiles showing traffic incidents at specified coordinates and zoom.
Get Traffic Incident ViewportTool to retrieve traffic incidents within a viewport defined by bounding box and zoom level.
List Geofencing Alert RulesTool to list geofencing alert rules with optional filtering.
List Geofencing Alerts HistoryTool to retrieve geofencing alert history within a specified time range.
List Geofencing ObjectsTool to list all tracked objects in the TomTom Geofencing system.
List Location History ObjectsTool to list objects with location history.
List Notification GroupsTool to list notification contact groups.
List POI CategoriesTool to retrieve all POI categories supported by TomTom Search API.
List Sprite VersionsTool to list available sprite asset versions.
Get Map CopyrightsTool to retrieve copyright information for a specific map tile.
MAP_DISPLAY_RASTER_TILETool to retrieve a raster map tile for specified coordinates and zoom.
Map Display Static ImageTool to fetch a static map snapshot given center coords and zoom.
Map Display WMS GetMapTool to retrieve a map image via WMS GetMap.
Matrix RoutingTool to calculate travel time and distance matrix between multiple locations.
Nearby SearchTool to find Points of Interest near a specified location.
Edit Contact Group (Partial)Tool to partially update a contact group in TomTom Notifications API.
Points of Interest SearchTool to search for points of interest by query.
Reverse GeocodeTool to convert geographic coordinates into a human-readable address.
Reverse Geocode Cross StreetTool to find the nearest cross street or intersection for given geographic coordinates.
Reverse Geocode OrbisTool to convert geographic coordinates into a human-readable address using TomTom's Orbis Maps API.
Search Along RouteTool to search for Points of Interest along a specified route with detour time constraints.
Search Along Route (v2)Tool to search for Points of Interest along a specified route using Search API v2.
Search GeometryTool to search for POIs within geometric areas (circles or polygons).
Orbis Category SearchTool to search for Points of Interest by category using TomTom Orbis Maps API.
Orbis Places SearchTool to perform fuzzy search for addresses and points of interest using TomTom Orbis Maps API.
Orbis POI SearchTool to search for points of interest using TomTom Orbis Maps API.
Snap to Roads (Sync)Tool to snap GPS points to the road network synchronously.
Structured GeocodeTool to convert structured address fields into coordinates.
Traffic IncidentsTool to retrieve detailed traffic incidents within a bounding box.
Update Geofencing SecretTool to change the customer secret for TomTom Geofencing API.
Update Notifications GroupTool to update an existing contact group in TomTom Notifications API.

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 you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

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

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

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

if (!process.env.OPENAI_API_KEY) 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,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["tomtom"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Tomtom tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Tomtom-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Tomtom tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to tomtom, like summarize my last 5 emails, send an email, etc... :)))\n",
);

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

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
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({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

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

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Tomtom tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Tomtom and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

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

if (!process.env.OPENAI_API_KEY) 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,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["tomtom"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to tomtom, like summarize my last 5 emails, send an email, etc... :)))\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({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

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

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Tomtom agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Tomtom MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Tomtom MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Tomtom MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Tomtom MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Tomtom MCP with Claude Cowork

Codex logo

Codex

Use Tomtom MCP with Codex

OpenClaw logo

OpenClaw

Use Tomtom MCP with OpenClaw

Hermes logo

Hermes

Use Tomtom MCP with Hermes

CLI logo

CLI

Use Tomtom MCP with CLI

Google ADK logo

Google ADK

Use Tomtom MCP with Google ADK

LangChain logo

LangChain

Use Tomtom MCP with LangChain

Mastra AI logo

Mastra AI

Use Tomtom MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Tomtom MCP with LlamaIndex

CrewAI logo

CrewAI

Use Tomtom MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Tomtom MCP?

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

Can I use Tool Router MCP with Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 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 Tomtom tools.

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

Yes, absolutely. You can configure which Tomtom 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 Tomtom 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↗