How to Use the TfL MCP in LangChain

Q: How can TfL and LangChain manage disruptions?

The getlinestatus tool checks the current state of all lines. Your agent runs this first to identify 'Severe Delays.' You then feed those specific line names into a call to getjourney so it only suggests viable alternatives.

Q: When planning for TfL bike routes with LangChain?

You can use the getbikepoints tool to list all docking stations nearby. After finding a suitable dock, you'll need the coordinates to feed into the getjourney function so it plans the final cycling leg of the trip.

Q: What if I search for an area using TfL and LangChain?

You can use getplacesearch to find POIs like museums or parks. Once you have a place ID, you'll need to run getstoppointdetails against it. This gives you the specific station type and accessibility info for that location.

Q: How does TfL data improve reliability with LangChain?

The system uses getarrivals to get predicted times, but your agent can cross-reference this against getroaddisruptions. If a road is closed, the ETA from the train station might be inaccurate for the final mile walk.

Build complex, multi-step reasoning pipelines for LangChain.

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 LangChain

Create your Vinkius account to connect TfL to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Step Journey Planning

The `get_journey` tool plans a trip using tube, bus, walking, or cycling segments. This allows your agent to calculate the optimal path from A to B while factoring in CO2 savings and fare estimates. You can chain this with `get_line_status`. First, check if the core lines are having major disruptions; then, use that status data when planning the journey. The output of one tool directly feeds into the next step.

Real-Time Incident Response

`get_road_disruptions` provides details like affected road segments and cause types (e.g., construction, incident). Your agent can first call this tool to check for A4 closures; next, it uses that data to inform a request to `get_arrivals`, adjusting expected times based on predicted traffic delays. This sequencing is critical when planning complex logistics. You're not just checking status; you're letting the results guide subsequent actions.

Advanced Location Contexting

Need to find a specific stop? Start by running `search_stop_point` to get IDs and modes served near a name. Then, pass that ID into `get_arrivals` to pull current predictions for buses or tubes at that spot. This two-step process ensures you're using precise data points instead of general estimates. It’s about building location awareness step by step.

Setup guide

Set up TfL MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes TfL tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tfl-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent TfL transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

The `get_line_status` tool checks the current state of all lines. Your agent runs this first to identify 'Severe Delays.' You then feed those specific line names into a call to `get_journey` so it only suggests viable alternatives.

You can use the `get_bike_points` tool to list all docking stations nearby. After finding a suitable dock, you'll need the coordinates to feed into the `get_journey` function so it plans the final cycling leg of the trip.

You can use `get_place_search` to find POIs like museums or parks. Once you have a place ID, you'll need to run `get_stop_point_details` against it. This gives you the specific station type and accessibility info for that location.

The system uses `get_arrivals` to get predicted times, but your agent can cross-reference this against `get_road_disruptions`. If a road is closed, the ETA from the train station might be inaccurate for the final mile walk.

The server handles all access via an endpoint token. When querying sensitive operational data like vehicle compliance (`get_vehicle_details`), your AI client must authenticate first to ensure the request is authorized.

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