How to Use the TfL MCP in Pydantic AI

Q: Why should I use Pydantic AI for complex TfL journey planning?

Pydantic guarantees the structure of the getjourney output. You know with certainty that every route option will contain total duration, fare estimates, and step-by-step instructions.

Q: How does Pydantic AI validate TfL service status?

The getlinestatus tool's output is validated against a strict schema. If the underlying TfL system sends unexpected data, your agent throws an explicit validation error instead of processing junk.

Q: Can Pydantic AI handle searching for various TfL stop points?

Yes, searchstoppoint returns a strictly typed object containing coordinates and mode served. This makes building reliable location-based features much easier.

Q: What type of data does this TfL MCP Server touch regarding vehicle compliance?

The getvehicledetails tool handles registration, make, model, and compliance status for vehicles, critical for ULEZ and Congestion Charge checks.

Write type-safe agents with Pydantic AI. Guaranteed TfL data structure correctness.

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 Pydantic AI

Create your Vinkius account to connect TfL to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Plan multi-modal journeys using MCP Server

The `get_journey` tool gives you a full breakdown of travel options, including total duration and specific line instructions. Crucially, the response schema defines every required field—you'll know exactly what fields to expect. This structured data prevents silent failures; if the API misses an expected transfer count, your agent fails loudly with validation error.

Check service reliability via MCP Server

The `get_line_status` tool provides detailed line status and disruption reasons. Since every response is validated against Pydantic models, you don't have to worry about receiving malformed severity levels. It guarantees that if the Victoria Line has a 'Severe Delays' status, it will arrive in the exact format your Python code expects.

Search for specific TfL stops using MCP Server

The `search_stop_point` tool finds matching points by name or location. Pydantic ensures you get all required metadata—like mode served, coordinates, and station hierarchy details—in a predictable structure. This level of type safety is vital when building production agents that depend on clean data inputs.

Setup guide

Set up TfL MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "tfl-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to TfL tools.",
)

result = await agent.run("List recent TfL transactions")
print(result.output)

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 Pydantic AI

Pydantic guarantees the structure of the `get_journey` output. You know with certainty that every route option will contain total duration, fare estimates, and step-by-step instructions.

The `get_line_status` tool's output is validated against a strict schema. If the underlying TfL system sends unexpected data, your agent throws an explicit validation error instead of processing junk.

Yes, `search_stop_point` returns a strictly typed object containing coordinates and mode served. This makes building reliable location-based features much easier.

The `get_vehicle_details` tool handles registration, make, model, and compliance status for vehicles, critical for ULEZ and Congestion Charge checks.

Nothing corrupts. The agent fails loudly with a validation error message, telling you exactly which field was incorrect or missing. No silent bugs—just clear, actionable errors.

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