How to Use the HERE Mobility MCP in Vercel AI SDK

Q: Can I build a real-time 'next train' display with this?

Yes, that's a perfect use case. Your app can call getschedule for a specific station ID. The AI SDK will stream the departure times right into your UI components, so you can build a live, auto-updating schedule board.

Q: What's the best way to find stations with HERE Mobility and the Vercel AI SDK?

Start with getnearbystations using the user's coordinates. Stream those results to a map. When the user taps a station, use its ID to call getstationdetails to show more info. It gives the user immediate feedback.

Build live transit UIs with HERE Mobility data streaming directly into your Vercel AI SDK app. See routes and schedules appear instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HERE Mobility MCP to Vercel AI SDK

Create your Vinkius account to connect HERE Mobility 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 HERE Mobility with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Trip Plans into Your UI

Let users watch their trip plan build in real-time. Your Vercel AI SDK app can call `discover_trips` and stream the results directly into your React or Next.js components. Instead of a loading spinner, users see departure times, transfers, and transport modes populate the screen as they're found. For more complex journeys, combine it with `search_multimodal_trips`. This lets you show combined public transit, walking, and scooter options, with each leg of the trip streaming into the UI. It's a much better experience than waiting for a full API response.

Populate Maps with Live Station Data

Give your users a live look at the transit around them. Use `get_nearby_stations` to find all stations within a set radius, streaming the names, lines, and coordinates to your map component. Each station can appear on the map the moment it's returned from the MCP server. Once a user clicks a station, you can instantly fetch its upcoming schedule with `get_schedule` or its facilities with `get_station_details`. Because you're using the AI SDK, this new data streams in without a full page reload, keeping the interface fast and responsive.

Interactive Routes with Vercel AI SDK

Don't just show a static route. Let your users interact with it. After finding a route with `discover_trips`, you can use the resulting trip ID to call `get_route_details`. This gives you the full step-by-step breakdown. You can stream these details into an expandable list, showing each leg of the journey. If a user wants to find a station by name, `get_stations_by_name` lets them type "Union Station" and see matching results appear character by character.

Setup guide

Set up HERE Mobility 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 HERE Mobility 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 HERE Mobility 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 HERE Mobility. 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 HERE Mobility 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 HERE Mobility MCP in Vercel AI SDK

It's all about the stream. Instead of your user waiting for all trip data to load, the Vercel AI SDK streams results as they come from the HERE Mobility tools. Your UI can render routes, stations, and schedules piece by piece, which feels much faster.

Yes, that's a perfect use case. Your app can call `get_schedule` for a specific station ID. The AI SDK will stream the departure times right into your UI components, so you can build a live, auto-updating schedule board.

Start with `get_nearby_stations` using the user's coordinates. Stream those results to a map. When the user taps a station, use its ID to call `get_station_details` to show more info. It gives the user immediate feedback.

It's focused on public transit but supports multiple modes. The `search_multimodal_trips` tool is designed to find routes that combine transit with walking, biking, or scooters, giving you a complete picture of urban mobility.

The server only processes the data your agent sends for a specific task, like origin and destination coordinates for a `discover_trips` call. It's all ephemeral. Vinkius ensures the server environment is sandboxed and doesn't store your query data after the request is complete.

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