How to Use the EMT Madrid (Open Data) MCP in Google ADK

Q: How do I initialize the EMT Madrid (Open Data) MCP Server in Google ADK?

Run pip install google-adk in your environment. Configure a StreamableHttpServerParameters object with your endpoint URL. Wrap that in an McpToolset and pass it to your LlmAgent.

Q: Can Google ADK filter the tools exposed by the EMT Madrid (Open Data) MCP Server?

You restrict the agent by passing a toolnames list to the toolset constructor. If you only want the agent to use getbusarrivals, you explicitly declare it. The model ignores the rest of the schema.

Q: Does the EMT Madrid (Open Data) integration work with Google ADK's long context?

Yes. The agent pulls the massive payload from listbicimadstations directly into the Gemini context window. The model processes the status of all Madrid stations simultaneously without truncation.

Q: How do I handle the EMT authentication flow?

The agent calls the login tool first. It extracts the access token from the response and includes it when querying the route planning or bus arrival endpoints.

Feed live EMT Madrid (Open Data) transit metrics into your Google ADK agents for enterprise-scale commuter analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EMT Madrid (Open Data) MCP to Google ADK

Create your Vinkius account to connect EMT Madrid (Open Data) 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 EMT Madrid (Open Data) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Integration for BiciMAD

The `list_bicimad_stations` tool dumps the live status of every bike dock in the city directly to your Google ADK agent. You pipe this station capacity data straight into BigQuery. Gemini analyzes the historical depletion rates alongside the real-time feed to predict which neighborhoods will run out of bikes first. You filter the exposed operations using the `tool_names` parameter in your `McpToolset` setup. If your analytics agent only needs bike data, you restrict it from touching the bus endpoints. This keeps the model focused.

Google ADK Route Generation

Your agent triggers the `plan_bus_route` tool to map transit paths across the Madrid grid. Gemini's massive context window ingests the entire coordinate response array without dropping waypoints. The model cross-references these routes against your internal logistics data stored in Google Cloud. The MCP server handles the external API communication. You just pass the `McpToolset` to your `LlmAgent` and request a route. The agent figures out the exact parameters required by the EMT endpoints.

Automated Token Management

The `login` tool fetches the required accessToken from EMT MobilityLabs. Your agent runs this authentication step before attempting to pull any transit data. It stores the token in context and applies it to subsequent requests. When you need live bus tracking, the agent hits `get_bus_arrivals` with the valid token. The HTTP transport layer manages the connection between your Google Cloud infrastructure and the Vinkius managed MCP server. You get the arrival times without writing custom API wrappers.

Setup guide

Set up EMT Madrid (Open Data) 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 EMT Madrid (Open Data) 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="EMT Madrid (Open Data)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to EMT Madrid (Open Data) 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 EMT Madrid. 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 EMT Madrid (Open Data) 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 EMT Madrid (Open Data) MCP in Google ADK

Run `pip install google-adk` in your environment. Configure a `StreamableHttpServerParameters` object with your endpoint URL. Wrap that in an `McpToolset` and pass it to your `LlmAgent`.

You restrict the agent by passing a `tool_names` list to the toolset constructor. If you only want the agent to use `get_bus_arrivals`, you explicitly declare it. The model ignores the rest of the schema.

Yes. The agent pulls the massive payload from `list_bicimad_stations` directly into the Gemini context window. The model processes the status of all Madrid stations simultaneously without truncation.

The agent calls the `login` tool first. It extracts the access token from the response and includes it when querying the route planning or bus arrival endpoints.

The server handles raw API credentials and precise user location coordinates for transit routing. Vinkius operates on a zero-trust architecture. Your Google Cloud environment connects to an ephemeral endpoint that instantly terminates after returning the transit payload.

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