How to Use the Comunidad de Madrid (Portal Regional) MCP in Google ADK

Q: How do I initialize the Comunidad de Madrid (Portal Regional) MCP Server with Google ADK?

Install the SDK with pip install google-adk. Instantiate McpToolset using the StreamableHttpServerParameters pointing to your Vinkius URL, then pass it to your LlmAgent tools list.

Q: Can I restrict which Comunidad de Madrid (Portal Regional) tools are exposed to Google ADK?

Yes, you can use the optional tool names filter in the McpToolset configuration. This lets you expose only searchdatastore while hiding administrative tools like listdatasets.

Q: Can my agent join Madrid portal data with BigQuery tables?

Yes. Your agent can fetch public data using searchdatastore and then use Google ADK's native BigQuery integrations to insert those records into your cloud warehouse.

Connect Gemini's million-token context to Comunidad de Madrid open data using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comunidad de Madrid (Portal Regional) MCP to Google ADK

Create your Vinkius account to connect Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Madrid Datastores via Google ADK

`search_datastore` feeds raw regional data directly into Gemini's massive context window. Your agent pulls thousands of rows of public records from the Madrid portal and processes them in a single prompt. Because this MCP Server integrates with the Google ADK, you can pipe the returned datastore results directly into BigQuery. This allows you to combine public Madrid metrics with your internal enterprise datasets.

Automated Catalog Discovery

`search_datasets` allows your Gemini agent to find relevant public files based on natural language queries. The agent searches across Madrid's catalog for topics like public health or traffic flow. After finding a match, `list_datasets` provides the identifiers needed to pull the actual data. The MCP Server handles the tool execution, letting Gemini decide which datasets to inspect based on your user's request.

Granular Resource Inspection

`get_resource` retrieves specific file metadata and download links from the Madrid portal. Your agent inspects the resource format, verifying whether it is a CSV, JSON, or XLS file before processing. Using `get_dataset` alongside this tool gives the agent a complete view of the dataset's schema. This prevents processing errors when Gemini passes the data to Vertex AI pipelines.

Setup guide

Set up Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) 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="Comunidad de Madrid (Portal Regional)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional). 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 Comunidad de Madrid (Portal Regional) 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 Comunidad de Madrid (Portal Regional) MCP in Google ADK

Install the SDK with `pip install google-adk`. Instantiate `McpToolset` using the `StreamableHttpServerParameters` pointing to your Vinkius URL, then pass it to your `LlmAgent` tools list.

Yes, you can use the optional tool names filter in the `McpToolset` configuration. This lets you expose only `search_datastore` while hiding administrative tools like `list_datasets`.

The server returns paginated JSON payloads from the Madrid portal. Gemini's long context easily digests these large chunks of regional metadata without running out of memory.

Yes. Your agent can fetch public data using `search_datastore` and then use Google ADK's native BigQuery integrations to insert those records into your cloud warehouse.

The MCP Server accesses read-only public datasets, eliminating the risk of modifying regional databases. All traffic between your Google Cloud environment and the Madrid portal is encrypted via HTTPS through the Vinkius gateway.

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