How to Use the Transport for London MCP in Mastra AI

Q: How does Transport for London journey planning work with Mastra AI?

Mastra AI uses getjourney to plan the route. If that fails due to a specific line issue, it can automatically pivot and use other tools like checking road status or bike points.

Q: Can I check multiple Transport for London lines with Mastra AI?

Yes. The getlinestatus tool supports comma-separated IDs (e.g., 'central,victoria') allowing your agent to check the status of several key TfL lines in one go.

Q: Does Mastra AI handle multiple Transport for London disruption sources?

It does. You can chain getroaddisruptions (for roads) with getlinestatus (for rail lines). This provides a comprehensive view of disruptions, not just one source.

Q: How do I get detailed info for bus stops and stations?

You use the searchstop tool to find matching IDs. Then you pass those specific IDs into getstopdetails to pull all necessary information before planning anything.

Automate complex transit operations with Mastra AI's workflow engine and MCP Server integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Transport for London MCP to Mastra AI

Create your Vinkius account to connect Transport for London to Mastra AI 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 Transport for London with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Advanced Multi-Step Journey Routing

Build failure-proof routing logic. The `get_journey` tool can plan the route, but you might need to check line status first using `get_line_status`. Mastra AI handles this sequence: if a core line is delayed, it automatically tries an alternative journey path. This workflow allows your agent to retry with different methods—like suggesting cycling instead of the Tube—if the primary route fails. It's built for complex operations.

Failure-Resistant Service Monitoring

Need to know if a line is running? Start by calling `get_line_status`. If it reports 'Severe Delays,' the workflow can then automatically run `get_road_disruptions` for that area. This chaining ensures you get all necessary failure details. The system handles these calls sequentially, ensuring that if one API call fails, it tries another method or notifies an admin.

Comprehensive Bike and Bus Availability Check

You can't just plan a trip; you gotta check the hardware. The `get_bike_points` tool reports bike availability, while `get_arrivals` confirms buses are coming. Mastra AI groups these calls together to give one complete picture. This makes it ideal for agents that need to handle physical assets and real-time schedules in a single, robust transaction.

Setup guide

Set up Transport for London MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Transport for London tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "transport-for-london-mcp-client",
  servers: {
    "transport-for-london-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Transport for London Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Transport for London tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Transport for London transactions"
);
console.log(result.text);

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 Transport for London. 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 Transport for London 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 Transport for London MCP in Mastra AI

Mastra AI uses `get_journey` to plan the route. If that fails due to a specific line issue, it can automatically pivot and use other tools like checking road status or bike points.

Yes. The `get_line_status` tool supports comma-separated IDs (e.g., 'central,victoria') allowing your agent to check the status of several key TfL lines in one go.

The server touches live transport operational data: bus arrivals, tube line statuses, major road congestion levels, and bike docking station availability. This is critical failure-handling info.

It does. You can chain `get_road_disruptions` (for roads) with `get_line_status` (for rail lines). This provides a comprehensive view of disruptions, not just one source.

You use the `search_stop` tool to find matching IDs. Then you pass those specific IDs into `get_stop_details` to pull all necessary information before planning anything.

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