How to Use the TfL MCP in Mastra AI

Q: How can mastra-ai manage TfL journey planning?

The agent runs a complex workflow starting with getjourney. It processes the output, checking both total duration and fare estimates. If initial results are poor, it automatically checks service status via getlinestatus to find better options.

Q: Does mastra-ai help with TfL accessibility planning?

Yes. You can build a specialized workflow that uses getplacesearch for a location, then calls getstoppointdetails. The agent validates the results to ensure step-free access or lift availability before suggesting the route.

Q: What if I need TfL road disruption alerts with mastra-ai?

The workflow can prioritize checking getroaddisruptions first. This ensures that even if a route looks good, the agent verifies current construction or incidents before presenting it to the user.

Build resilient transport agents with mastra-ai.

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 Mastra AI

Create your Vinkius account to connect TfL to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Check service and compliance in sequence.

You can build a multi-step workflow that first calls `get_line_status` to check if the Jubilee Line is suspended. If it is, your agent automatically triggers another tool call: `get_road_disruptions` to see if surface transport alternatives are viable. This pattern of conditional checking—if line status fails, then check roads—is what makes a resilient agent using this MCP Server.

Verify vehicle requirements for travel.

Building a trip planner that accounts for driving compliance? Your agent runs `get_vehicle_details` to verify if the car is ULEZ compliant. If it fails, the workflow branches and automatically suggests using an alternative transport mode. The MCP Server supports this kind of complex decision-making by integrating vehicle checks with route planning.

Plan journeys that account for failures.

The agent can execute a trip plan from `get_journey`, but it's smarter. It first calls `get_road_disruptions` to see if the primary road segment is closed. If so, it doesn't just fail; it retries by calling `get_place_search` for nearby alternatives, providing the user with multiple options. Mastra AI handles these automatic retries and conditional branches perfectly.

Setup guide

Set up TfL 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 TfL 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: "tfl-mcp-client",
  servers: {
    "tfl-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent TfL 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 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 Mastra AI

The agent runs a complex workflow starting with `get_journey`. It processes the output, checking both total duration and fare estimates. If initial results are poor, it automatically checks service status via `get_line_status` to find better options.

Yes. You can build a specialized workflow that uses `get_place_search` for a location, then calls `get_stop_point_details`. The agent validates the results to ensure step-free access or lift availability before suggesting the route.

The workflow can prioritize checking `get_road_disruptions` first. This ensures that even if a route looks good, the agent verifies current construction or incidents before presenting it to the user.

The framework supports this by allowing multi-step logic: first check `get_bike_points` for availability, then run a modified journey plan that includes cycling segments. It handles the sequential data processing.

While this MCP Server doesn't expose specific rate limit tools, Mastra AI’s underlying architecture supports robust error handling and built-in exponential backoff. This means if a call fails due to overload, the agent retries automatically without crashing.

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