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

Q: Can AutoGen agents argue about which theme in Datos.gob.es (Catálogo Nacional) is most relevant to my query?

Yes. You can have one agent propose a theme from listthemes, and a second agent critique it based on the query's keywords. They can debate until they agree on the best theme to use with listdatasetsbytheme.

Equip your AutoGen agents to debate and analyze Spain's open data, reaching better-informed conclusions.

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 AutoGen

Create your Vinkius account to connect Datos.gob.es (Catálogo Nacional) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Search Strategies

AutoGen shines when there's no single right answer. One agent can propose using `search_datasets_by_title` to find data. A critic agent can challenge that, suggesting that a broader keyword search with `list_datasets_by_keyword` might be more effective. They'll debate, test their ideas using the tools, and converge on the best way to find the information you need from the Datos.gob.es catalog. It's a collaborative approach to discovery.

Assign Agents to Analyze Data

Task one agent to be the 'Regional Analyst'. It uses `list_regions` and `list_provinces` to understand the geographic breakdown of the data. A second 'Sector Specialist' agent uses `list_public_sectors` and `list_themes` to explore by industry. They are not just running tools; they are embodying a point of view. They use this MCP server to pull their respective data points, then present their findings to a manager agent. This multi-perspective analysis leads to a more nuanced understanding than a single agent could achieve.

Build Consensus with This AutoGen MCP Server

Imagine you need the 'best' dataset on commerce. An 'Explorer' agent uses `list_datasets_by_theme` with 'comercio', while a 'Validator' agent checks the format of each result using `list_distributions_by_dataset`. They'll go back and forth until they agree on a dataset that is both on-topic and available in CSV. This conversation ensures you get a verified result, not just the first thing a tool returns. The final answer has been debated and agreed upon by multiple specialized agents.

Setup guide

Set up Datos.gob.es (Catálogo Nacional) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Datos.gob.es (Catálogo Nacional) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Datos.gob.es (Catálogo Nacional)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Datos.gob.es (Catálogo Nacional) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Datos.gob.es (Catálogo Nacional)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Datos.gob.es (Catálogo Nacional) data")
    print(result.messages[-1].content)

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 AutoGen

Absolutely. That's a perfect use case. The first agent calls `list_publishers`. A user or proxy agent selects one, and a second agent takes that publisher's ID and uses `list_datasets_by_publisher` to get their specific datasets.

The tool call will fail, and AutoGen's framework allows another agent to notice the failure. A 'debugger' or 'critic' agent can then suggest an alternative, like using `search_datasets_by_title` to find the correct ID first.

Yes. You can have one agent propose a theme from `list_themes`, and a second agent critique it based on the query's keywords. They can debate until they agree on the best theme to use with `list_datasets_by_theme`.

Yes, but it's more direct to filter distributions. An agent can call `list_distributions_by_format` with a common format like 'CSV' or 'JSON' to see what's available.

It's secure. This server only deals with public metadata from Spain's data catalog, like dataset URIs and modification dates. Vinkius provides a zero-trust environment where your connection is authenticated with a single token. Each agent's tool call runs in an ephemeral session that's wiped clean afterward, leaving no trace.

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