How to Use the MTA MCP in AutoGen

Q: How do I register MTA MCP Server tools with my AutoGen agents?

Use the mcpservertools adapter from autogen-ext to fetch the tools from the Vinkius URL. Pass this list directly to your AssistantAgent during initialization.

Q: Can multiple AutoGen agents query the MTA server at the same time?

Yes. Your agents can query different tools like getsubwayfeed and getbuspredictions concurrently. The MCP server handles these requests in parallel to keep your multi-agent conversations fast.

Q: What is the best way to get arrival predictions for a specific bus?

Have your agent call getbuspredictions with the stop ID. If you need targeted predictions for a single route, use getbusestimatedarrival instead.

Let AutoGen agents debate transit options using real-time MTA subway, bus, and commuter rail data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MTA MCP to AutoGen

Create your Vinkius account to connect MTA 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 MTA with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Transit Consensus using MTA MCP Server

`get_service_alerts` provides the raw data for your security and routing agents to debate transit safety. One AutoGen agent analyzes active delays while another tracks live train positions via `get_subway_feed` using these MCP server tools. They coordinate to find the fastest path, negotiating transfers based on real-time track conditions. This multi-agent setup ensures your users get routes that bypass active bottlenecks.

Coordinated Commuter Rail and Subway Routing

`get_lirr_feed` monitors the Long Island Rail Road while `get_metro_north_feed` tracks northern commuter lines. Separate AutoGen agents manage these feeds independently to watch for incoming delays. A central coordinator agent uses `get_system_time` to synchronize schedules across both rail networks. This prevents missed connections when transferring from commuter trains to the subway.

Micro-Level Bus Fleet Coordination

`get_bus_vehicle_at_stop` tracks buses approaching a specific stop. Your agent uses this tool to monitor distance and estimated arrival times for immediate connections. If a bus is delayed, the agent queries `get_bus_routes` to find alternative lines servicing the same area. The agents debate whether walking or waiting is the faster option based on current speed data from `get_bus_vehicles`.

Setup guide

Set up MTA 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 MTA 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="MTA_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` adapter from `autogen-ext` to fetch the tools from the Vinkius URL. Pass this list directly to your `AssistantAgent` during initialization.

Yes. Your agents can query different tools like `get_subway_feed` and `get_bus_predictions` concurrently. The MCP server handles these requests in parallel to keep your multi-agent conversations fast.

You can design a critic agent that compares subway delays from `get_service_alerts` against live train arrival times from `get_subway_feed`. The agents debate the ground truth before presenting a final route to the user.

Have your agent call `get_bus_predictions` with the stop ID. If you need targeted predictions for a single route, use `get_bus_estimated_arrival` instead.

Every request goes through an ephemeral, zero-trust V8 isolate sandbox. Your transit queries, stop IDs, and coordinates are processed in memory and destroyed instantly after execution.

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