How to Use the LA Metro MCP in AutoGen

Let your AutoGen agents debate the best way to cross LA using real-time Metro data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LA Metro MCP to AutoGen

Create your Vinkius account to connect LA Metro 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 LA Metro with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate the Fastest Route

This is where AutoGen shines. One agent, the "Planner," uses `get_bus_schedule` to propose a route. A second agent, the "Realist," immediately checks `get_bus_locations` and `get_service_alerts`. The Realist can then counter the plan: "That route looks good on paper, but the buses are all bunched up downtown and there's a delay reported at 7th Street. We should use the train instead." It's a conversation that leads to a better, more realistic plan.

Assign Roles for Trip Planning

You can build a team of specialized agents. Create a "Rail Expert" that only has access to tools like `get_rail_to_rail` and `get_rail_stations`. Make a "Bus Expert" that uses `get_bus_routes` and `get_stop_predictions`. Add a "Safety Officer" that does nothing but monitor `get_service_alerts`. When you give them a task like "plan a trip to LAX," they collaborate. Each agent contributes its specific expertise, and they work together in a chat to build a comprehensive itinerary. It's like having a miniature transit control room.

Consensus-Driven Commuting via MCP Server

A single agent might make a simple choice. A team of AutoGen agents can find a smarter one. For example, your "Efficiency" agent might see a bus arriving in 2 minutes using `get_stop_predictions` and tell you to run. But a "Patience" agent could use `get_bus_vehicles` to see that the first bus is packed, and a second, emptier bus is just 5 minutes behind it. They can discuss this and present you with a consensus: wait for the better option. This MCP server gives them the raw data they need to have that debate.

Setup guide

Set up LA Metro 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 LA Metro 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="LA Metro_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent LA Metro 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="LA Metro_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent LA Metro 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 LA Metro. 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 LA Metro 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 LA Metro MCP in AutoGen

Yes. You can create multiple agents, give them different goals (e.g., fastest time vs. fewest transfers), and provide them all with the LA Metro tools. They will then debate the trade-offs to find a solution, with each agent using tools like `get_rail_to_rail` to support its argument.

When you define each agent in your AutoGen setup, you pass a specific list of tools to its configuration. One agent might get the `get_rail_*` tools, while another gets the `get_bus_*` tools, enabling them to specialize.

You can tackle problems that require balancing competing priorities. For instance, planning a trip for a large group that optimizes for cost, time, and walking distance, while also actively monitoring `get_service_alerts` for disruptions and re-planning on the fly.

Absolutely. You can create a dedicated "monitor" agent and give it access to only one tool: `get_service_alerts`. This agent can be part of a group chat and interrupt the conversation only when a relevant new alert is posted.

The agents share information in a group chat. If one agent calls `get_rail_arrivals` and gets a list of arrival times, it posts that raw data or a summary of it into the chat for the other agents to see and react to. This conversation log is typically held in memory during the session.

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