How to Use the LA Metro MCP in Google ADK

Q: Can I restrict which LA Metro MCP Server tools the Google ADK agent can access?

Yes. You can pass an optional toolnames list to your toolset initialization. This restricts the agent to specific tools, like only allowing getrailarrivals while hiding bus endpoints.

Q: How does Google ADK handle high-frequency polling of the LA Metro MCP Server?

We recommend caching static responses like getbusschedule locally. For real-time endpoints like getbusvehicles, implement a smart back-off strategy to avoid hitting transit API rate limits.

Deploy enterprise Gemini agents using Google ADK to analyze real-time LA Metro transit data and long-term schedules.

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 Google ADK

Create your Vinkius account to connect LA Metro 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 LA Metro with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise transit analysis using Google ADK

Analyzing large-scale transit networks requires pulling real-time coordinates from `get_bus_locations` and `get_rail_vehicle_positions`. This feeds raw spatial data directly into your long-context reasoning models. You can easily correlate this live data with historical transit records stored in BigQuery. This allows your enterprise agent to run deep analyses on fleet efficiency and actual arrival accuracy across the county.

System-wide route and stop mapping

Mapping the complete transit network requires querying `get_bus_routes` and `get_bus_stops` to build a complete spatial directory. The Google ADK structures these outputs, making them instantly searchable for complex queries. For rail operations, the agent queries `get_rail_stations` and `get_rail_routes` to map out the entire subway and light rail network. This provides the foundational geography your agent needs to answer complex commuter routing questions.

Real-time arrival predictions at scale

Retrieving accurate wait times requires calling `get_stop_predictions` and `get_rail_arrivals` for active transit points. The framework handles the high-throughput demands of enterprise transit applications. This MCP Server allows your agent to check `get_service_alerts` to dynamically adjust predictions. Commuters get accurate updates even during major track maintenance or traffic gridlock — which is basically every Tuesday.

Setup guide

Set up LA Metro 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 LA Metro 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="LA Metro_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LA Metro 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 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 Google ADK

Use the McpToolset class with your HTTP server parameters to register the endpoint. Pass this toolset directly to your LlmAgent constructor to expose all twelve transit tools to your Gemini models.

Yes. You can pass an optional tool_names list to your toolset initialization. This restricts the agent to specific tools, like only allowing `get_rail_arrivals` while hiding bus endpoints.

We recommend caching static responses like `get_bus_schedule` locally. For real-time endpoints like `get_bus_vehicles`, implement a smart back-off strategy to avoid hitting transit API rate limits.

Absolutely. Gemini's million-token context window easily ingests the entire list of stations returned by `get_rail_stations`, allowing the model to reason about complex, multi-line transit paths.

Yes. The server only queries public transit data like bus schedules and vehicle coordinates. It does not collect, log, or share individual user coordinates or search histories, keeping commuter queries completely anonymous.

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