How to Use the Transport for London MCP in AutoGen

Q: If I use Transport for London and AutoGen, what is the benefit of MCP Server?

The MCP Server provides standardized tools—like getstopdetails or getlinedetail—that multiple agents can call reliably. This consistent set of functions allows them to argue using verifiable, structured data.

Force consensus on complex routes with AutoGen and the Transport for London MCP Server.

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 AutoGen

Create your Vinkius account to connect Transport for London to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Optimal Routes with AutoGen

AutoGen's strength is that agents debate. You can set up a 'Planner Agent' to call `get_journey` and propose a route, while a 'Safety Agent' simultaneously calls `get_road_disruptions`. They then negotiate which route minimizes risk based on the conflicting data. The MCP Server provides multiple viewpoints—one agent focuses purely on speed (using `get_arrivals`), and another focuses on cost (using fare info from `get_journey`). The conversation converges on the best actionable plan.

Multi-Perspective Status Checks with AutoGen

Need to know if travel is possible? Set up an agent group. One 'Rail Agent' calls `get_line_status`, another 'Road Agent' calls `get_road_status`. They discuss the findings: 'The tube is fine, but the main road leading to it has Severe Delays.' This multi-agent approach finds the gaps in data. The MCP Server gives you inputs for both rail and surface transit status checks.

Automated Stop Verification with AutoGen

An agent needs a stop ID before it can check arrivals. Instead of manually supplying it, the 'Search Agent' calls `search_stop` first. It gets a list of potential IDs and then passes that vetted list to the final 'Arrival Agent' for accurate predictions via `get_arrivals`. The system self-corrects through conversation. This process ensures all inputs are validated against the actual transport network data.

Setup guide

Set up Transport for London MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Transport for London tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Transport for London_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Transport for London data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Transport for London_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Transport for London data")
    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 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 AutoGen

AutoGen's core function is resolution. If one agent sees Minor Delays on a tube line (`get_line_status`) and another sees an optimal route via `get_journey`, the agents debate the merits until they agree on the most actionable path.

Yes. You can simulate a full journey: one agent checks bike availability (`get_bike_points`), another checks current road conditions, and a third combines this into an optimized multi-modal plan.

The MCP Server provides standardized tools—like `get_stop_details` or `get_line_detail`—that multiple agents can call reliably. This consistent set of functions allows them to argue using verifiable, structured data.

This server touches a wide range of live operational metrics: predicted arrival times (from `get_arrivals`), real-time line status (from `get_line_status`), and major road congestion details (from `get_road_status`).

It does. Agents can automatically check bike availability using `get_bike_points` before suggesting a cycling portion of the trip, making sure the physical resources are available at the destination.

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