How to Use the TfL MCP in Vercel AI SDK

Q: How does ai-sdk handle TfL arrival predictions?

The ai-sdk streams data directly from the MCP Server. When you query getarrivals, your client receives updates in real time, so the user sees predicted times appearing instantly rather than waiting for a loading spinner.

Q: Can I use ai-sdk to plan bike journeys?

Absolutely. The server provides three tools—getbikepoints, getbikepoint, and getbikepoints—to manage Santander Cycles data. Your agent can build a multi-modal trip using these bikes alongside the main journey planner.

Q: What if I need TfL status in my app with ai-sdk?

You use getlinestatus to check service reliability across all lines. This is a key data point for any good transport app. The MCP Server helps you show users whether the Overground has Minor Delays or if everything's running Good Service.

Q: Is ai-sdk reliable for complex TfL routes?

Yes, ai-sdk handles the streaming of complex data. For trips from Paddington to Greenwich, it streams the detailed leg-by-leg instructions from getjourney, allowing your users to follow the plan in real time.

Q: What types of TfL data does this MCP Server support with ai-sdk?

This server covers everything: tube arrivals via getarrivals, road closures using getroaddisruptions, and bike availability through the dedicated cycle tools. It's a comprehensive source for London transport.

Build real-time transport UIs with ai-sdk.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TfL MCP to Vercel AI SDK

Create your Vinkius account to connect TfL to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup TfL with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Stream live arrival data.

When you call `get_arrivals`, your AI client streams back predicted times and line names for any specific TfL stop point. Instead of waiting for a batch response, the user sees the next Northern Line train appear on screen as soon as the data hits. This live flow is perfect for building modern interfaces where instant feedback matters. You can easily reference `get_arrivals` to show users exactly when and what kind of service (tube, bus, etc.) they're waiting for.

Map points and services.

Need to build out a map showing every potential stop? Use the `get_place_search` tool. It returns place IDs, names, categories, and coordinates, letting your user see where they are in London. If you combine this with `get_stop_point_details`, you can give users specific metadata—like whether a station has step-free access or which modes it serves. This builds out the full context around any point of interest.

Track road closures instantly.

Traffic disruptions kill user trust. Calling `get_road_disruptions` provides immediate alerts on affected segments, severity levels, and cause types (like roadworks or incidents). Your UI can display this warning right away. This is critical for showing alternative ways to travel. By combining `get_road_disruptions` with a journey plan from `get_journey`, your agent ensures the user sees both the planned trip and any roadblocks affecting it.

Setup guide

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

The `ai-sdk` streams data directly from the MCP Server. When you query `get_arrivals`, your client receives updates in real time, so the user sees predicted times appearing instantly rather than waiting for a loading spinner.

Absolutely. The server provides three tools—`get_bike_points`, `get_bike_point`, and `get_bike_points`—to manage Santander Cycles data. Your agent can build a multi-modal trip using these bikes alongside the main journey planner.

You use `get_line_status` to check service reliability across all lines. This is a key data point for any good transport app. The MCP Server helps you show users whether the Overground has Minor Delays or if everything's running Good Service.

Yes, `ai-sdk` handles the streaming of complex data. For trips from Paddington to Greenwich, it streams the detailed leg-by-leg instructions from `get_journey`, allowing your users to follow the plan in real time.

This server covers everything: tube arrivals via `get_arrivals`, road closures using `get_road_disruptions`, and bike availability through the dedicated cycle tools. It's a comprehensive source for London transport.

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