How to Use the Datos.gob.es (Catálogo Nacional) MCP in Google ADK

Q: How do I configure Datos.gob.es (Catálogo Nacional) with Google ADK?

Import McpToolset and configure it with StreamableHttpServerParameters. Pass the resulting object to your LlmAgent via the tools array. The Vinkius endpoint handles the authentication automatically.

Q: Can Google ADK models search Datos.gob.es (Catálogo Nacional) by keywords?

They absolutely can. The listdatasetsbykeyword tool maps directly to the catalog's search engine. Gemini will generate the right Spanish search terms based on your English prompts.

Q: How do I restrict this MCP Server to specific tools?

Pass a toolnames list when initializing the toolset. If you only want your agent looking up categories, restrict it to listthemes and listpublicsectors.

Q: Does this integration work with BigQuery pipelines?

Yes. Your agent can use getdataset to find the exact download URI for a Spanish government dataset, then write a Python script to ingest that CSV directly into your BigQuery tables.

Feed Spanish government metadata directly into your Google ADK pipelines and analyze massive datasets with Gemini's long context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datos.gob.es (Catálogo Nacional) MCP to Google ADK

Create your Vinkius account to connect Datos.gob.es (Catálogo Nacional) 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 Datos.gob.es (Catálogo Nacional) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK agents for public data

Enterprise workflows on Google Cloud often require external public records to enrich internal BigQuery tables. Connecting this MCP Server lets your Gemini models query Spain's national catalog autonomously. You initialize `McpToolset` with the Vinkius URL, and your agent immediately understands how to navigate Spanish government taxonomies. Gemini's massive context window changes how you handle the results. When you call `list_datasets`, the agent can dump hundreds of dataset descriptions into memory at once. It reads through the entire payload to find exactly what your GCP pipeline needs without losing track of the original prompt.

Target specific Spanish regions

Geographic filtering is built right into the toolset. Your agent can isolate regional data by hitting `list_regions` to find the ID for Catalonia or Andalusia. From there, it chains into `list_datasets_by_spatial` to pull records specific to that exact autonomous community. You control exactly which capabilities the model sees. Using the `tool_names` filter in your setup restricts the agent to just `get_province` and `get_country_spain` if you only want it doing location lookups. This keeps the prompt lean and prevents the agent from wandering into unrelated API endpoints.

Filter distributions by format

Pulling raw files requires knowing what formats exist in the catalog. The agent executes `list_distributions_by_format` to find structured data like CSVs that play nicely with Vertex AI. It ignores formats that require manual parsing. Finding who published the data takes one step. Calling `list_publishers` returns the specific government entities, which the agent then uses with `list_datasets_by_publisher`. Your Gemini model cross-references these publishers against your internal compliance lists instantly.

Setup guide

Set up Datos.gob.es (Catálogo Nacional) 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 Datos.gob.es (Catálogo Nacional) 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="Datos.gob.es (Catálogo Nacional)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Datos.gob.es (Catálogo Nacional) 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 Datos.gob.es. 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 Datos.gob.es (Catálogo Nacional) 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 Datos.gob.es (Catálogo Nacional) MCP in Google ADK

Import `McpToolset` and configure it with `StreamableHttpServerParameters`. Pass the resulting object to your `LlmAgent` via the `tools` array. The Vinkius endpoint handles the authentication automatically.

They absolutely can. The `list_datasets_by_keyword` tool maps directly to the catalog's search engine. Gemini will generate the right Spanish search terms based on your English prompts.

Pass a `tool_names` list when initializing the toolset. If you only want your agent looking up categories, restrict it to `list_themes` and `list_public_sectors`.

Yes. Your agent can use `get_dataset` to find the exact download URI for a Spanish government dataset, then write a Python script to ingest that CSV directly into your BigQuery tables.

You are querying public Spanish sector classifications, dataset distributions, and regional IDs. The Vinkius zero-trust architecture ensures that when your Gemini model requests records from specific ministries, those HTTP calls happen inside an isolated, short-lived sandbox that destroys itself after execution.

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