How to Use the CTA MCP in AutoGen

Q: Can AutoGen agents negotiate routes using CTA transit data?

Yes, you can set up one agent to pull arrival times using gettrainarrivals and another to check weather or traffic. They will discuss the options and output a coordinated plan.

Q: What is the best way to handle CTA service alerts in AutoGen?

Assign a specific monitoring agent to run getservicealerts periodically. If it finds a delay, it can trigger a conversation with the routing agent to update active travel itineraries.

Let your AutoGen agents debate and coordinate transit routes using real-time Chicago bus and train data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CTA MCP to AutoGen

Create your Vinkius account to connect CTA 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 CTA with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents coordinate CTA trips

`get_route_status` pulls the current operational health of all train lines and bus routes in Chicago. In an AutoGen setup with this MCP Server, a transit monitoring agent can share this status with a routing agent to negotiate the fastest travel path. One agent flags delays while another searches for alternative bus lines. They collaborate and converge on the best route based on actual, live service disruptions.

Track active Chicago buses across multi-agent systems

`get_bus_predictions` gets real-time arrival minutes for any specified stop ID. Your dedicated dispatcher agent can call this tool while a separate communication agent formats the alerts for the user. AutoGen handles the conversation flow between these specialized agents. This separation of concerns ensures your system stays responsive even during heavy transit delays.

Verify system times across your AutoGen MCP Server

`get_system_time` retrieves the official CTA server timestamp to synchronize all agent actions. Your coordinator agent uses this timestamp to calibrate prediction windows before running multi-agent simulations. This tool provides a quick connectivity check for your agents. It ensures all system clocks align before agents start querying real-time positions.

Setup guide

Set up CTA 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 CTA 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="CTA_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the AutoGen MCP adapter to fetch the tools from your Vinkius server URL. Pass the adapter's tool list directly to your AssistantAgent constructor.

Yes, you can set up one agent to pull arrival times using `get_train_arrivals` and another to check weather or traffic. They will discuss the options and output a coordinated plan.

Assign a specific monitoring agent to run `get_service_alerts` periodically. If it finds a delay, it can trigger a conversation with the routing agent to update active travel itineraries.

Yes, the Vinkius platform provides a secure HTTP endpoint that maps directly to AutoGen's streamable HTTP server parameters.

All transit queries and stop coordinates are processed in a secure, ephemeral sandbox. Your queries are never saved, keeping your agents' travel planning completely private.

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