How to Use the CTA MCP in Google ADK

Q: Can I use Google ADK to log all CTA train positions over time?

Yes. You can build a Google ADK agent that calls the gettrainpositions tool on a schedule. It can then pipe the returned train locations, run numbers, and timestamps into a Google Cloud service like BigQuery for storage and analysis.

Q: Does this MCP Server provide CTA train line colors for a Google ADK agent?

Absolutely. Both gettrainarrivals and gettrainpositions include line color data (e.g., 'Red', 'Blue', 'Brn'). This lets your agent provide more user-friendly information, like "The next Red Line train is arriving" instead of just a route code.

Q: What's the best way to check if the CTA API is responsive?

Have your agent call the getsystemtime tool. It's a lightweight request that simply returns the CTA's server time. A successful response confirms connectivity and authentication without using a more complex query.

Connect your Google ADK agent to live CTA data for building enterprise-grade transit tools on Google Cloud.

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 Google ADK

Create your Vinkius account to connect CTA to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Live Vehicle Positions Across Chicago

Your agent can now track Chicago's entire transit fleet. The `get_bus_vehicles` and `get_train_positions` tools provide real-time coordinates, route info, and speed for every bus and L train. You can query the whole system or filter down to a single line, like the Blue Line to O'Hare. This isn't just about dots on a map. With Google ADK, you can stream this location data into BigQuery for historical analysis or use it with Vertex AI to predict service bottlenecks. This MCP Server gives your agent the raw, real-time data to make it happen.

Power Your Google ADK Agent with Real ETAs

Give your agent the ability to provide precise arrival times. The `get_train_arrivals` and `get_bus_predictions` tools connect directly to the CTA's own prediction feeds. Your agent receives arrival times in minutes, destination info, and even run numbers. A Google ADK agent can use this to build powerful conversational flows. For example, it can find a station ID, check for upcoming trains with `get_train_arrivals`, and then cross-reference with `get_service_alerts` to make sure there are no surprise delays.

Map the Entire CTA Network

Before your agent can plan a trip, it needs to understand the system's structure. The `get_bus_routes`, `get_route_directions`, and `get_bus_stops` tools provide the necessary building blocks. Your agent can list all routes, find out which directions they run, and get the exact coordinates of every stop. This is the static data that gives context to the real-time feeds. A sophisticated agent can use this information to suggest routes, find nearby stops, or even analyze service coverage in different neighborhoods. This MCP provides a complete toolset for both static and dynamic data.

Setup guide

Set up CTA MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CTA tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CTA_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CTA tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

It can't search by street name directly. The agent should first use `get_bus_routes` to find routes that serve that area, then use `get_bus_stops` with a route ID to list all stops. It can then filter those stops by name to find the ones on Michigan Ave.

Yes. You can build a Google ADK agent that calls the `get_train_positions` tool on a schedule. It can then pipe the returned train locations, run numbers, and timestamps into a Google Cloud service like BigQuery for storage and analysis.

Absolutely. Both `get_train_arrivals` and `get_train_positions` include line color data (e.g., 'Red', 'Blue', 'Brn'). This lets your agent provide more user-friendly information, like "The next Red Line train is arriving" instead of just a route code.

Have your agent call the `get_system_time` tool. It's a lightweight request that simply returns the CTA's server time. A successful response confirms connectivity and authentication without using a more complex query.

The agent accesses public transit information, including bus positions, train arrival predictions, and route maps. Your connection to the CTA MCP Server runs in an ephemeral Vinkius sandbox. This means the environment is created just for your request and torn down immediately after, leaving no data behind.

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