How to Use the TomTom MCP in LangChain

Q: How can I find a physical address using TomTom and LangChain?

Run reversegeocoding with coordinates, and it hands you the corresponding street address. This is perfect for converting raw GPS data into human-readable text right in your chain.

Q: What if I need to query traffic incidents using TomTom and LangChain?

You must provide a min/max bounding box when calling gettrafficincidents. The tool then returns real-time data, so always validate your coordinates before running the chain.

Q: Can I use TomTom to find points of interest using LangChain?

Yes. Use searchpoibycategory with a category like 'hospital' and center coordinates. This tool populates your next step, allowing you to then fetch deep metadata for the top results.

Build multi-step reasoning with LangChain using TomTom's global mapping data.

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 LangChain

Create your Vinkius account to connect TomTom to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Routing Logic for LangChain

You need to calculate a route, but you only have an address string. Run `fuzzy_geocoding` first; it converts that fuzzy input into precise coordinates. Next, feed those coordinates directly into `calculate_route`. This sequence lets your agent determine the exact travel time and path between two points, making complex navigation logic straightforward.

Real-Time Traffic Analysis with MCP Server

Checking traffic isn't one step. First, use `get_traffic_incidents` to map out all current roadblocks in a bounding box. Then, narrow your scope by running `get_traffic_flow_segment`, which pulls the specific speed and quality data for key road segments. This two-step process allows your agent to build a full picture of traffic conditions before suggesting an alternate route.

Location Discovery using LangChain

Don't just look up an address. If you need to find the nearest gas station, start by calling `search_poi_by_category` with a category and coordinates. This returns a list of nearby points. If you then want detailed hours for one of those locations, use its ID in `get_poi_details`. LangChain chains these tools together so your agent makes intelligent decisions step-by-step.

Setup guide

Set up TomTom MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes TomTom tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tomtom-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent TomTom transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Run `reverse_geocoding` with coordinates, and it hands you the corresponding street address. This is perfect for converting raw GPS data into human-readable text right in your chain.

You must provide a min/max bounding box when calling `get_traffic_incidents`. The tool then returns real-time data, so always validate your coordinates before running the chain.

Yes. Use `search_poi_by_category` with a category like 'hospital' and center coordinates. This tool populates your next step, allowing you to then fetch deep metadata for the top results.

Absolutely. If you have explicit components—like a country code and postal code—use `structured_geocoding`. It gives you precise coordinates, which is much better than fuzzy matching.

This MCP Server touches location data (coordinates and addresses). The system handles input tokens via a single endpoint token, keeping your data managed within Vinkius's zero-trust environment.

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