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

Q: How do I install Datos.gob.es (Catálogo Nacional) into Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Initialize MCPToolset with your Vinkius URL and pass it to your Agent's toolsets parameter. Do not use the deprecated MCPServerHTTP class.

Q: How do I search by theme using this integration?

Your agent will call listthemes to get the valid categories, then pass the exact validated ID into listdatasetsbytheme. The type system ensures the agent doesn't invent non-existent themes.

Strictly validate Spanish open data API responses in Pydantic AI before your agent attempts to process them.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe access via MCP Server

Government APIs change without warning, which usually breaks autonomous workflows. Hooking this MCP Server into Pydantic AI ensures every response from the Spanish data catalog matches your expected schema. If the government adds an unexpected field to a dataset record, your agent fails loudly with a validation error instead of silently corrupting your database. Setup requires the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Once connected, tools like `list_datasets` and `get_dataset` become fully typed Python functions. Your chosen LLM knows exactly what parameters to provide.

Validate geographic and sector queries

Precision matters when querying public sector taxonomies. When your agent calls `get_public_sector` or `get_region`, Pydantic AI verifies the ID format before the HTTP request even leaves your machine. It prevents hallucinated province codes from wasting API calls. Complex spatial queries work exactly the same way. The `list_datasets_by_spatial` tool expects specific geographic scope parameters. Your agent constructs the query, Pydantic validates the structure, and the exact records for Basque Country or Madrid return in a predictable JSON format.

Strict distribution filtering

You need to know exactly what file types you are downloading. The agent triggers `list_distributions_by_format` to locate CSV or XML files. Because Pydantic AI enforces strict typing, your downstream code can trust that the returned format string actually matches your request. Searching by modification date requires identical rigor. Calling `list_datasets_by_date` forces the LLM to format timestamps correctly. If the model hallucinates a weird date string, the framework rejects it instantly, keeping your catalog searches completely accurate.

Setup guide

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

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "datosgobes-catalogo-nacional-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Datos.gob.es (Catálogo Nacional) tools.",
)

result = await agent.run("List recent Datos.gob.es (Catálogo Nacional) transactions")
print(result.output)

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 Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Initialize `MCPToolset` with your Vinkius URL and pass it to your Agent's `toolsets` parameter. Do not use the deprecated `MCPServerHTTP` class.

Yes. If the Spanish catalog returns an unexpected JSON structure for a dataset, Pydantic AI throws a runtime validation error. This prevents your agent from making decisions based on malformed government data.

The framework is completely model-agnostic. You can route queries through Ollama or vLLM, and they will interact with tools like `list_publishers` exactly the same way GPT-4 would.

Your agent will call `list_themes` to get the valid categories, then pass the exact validated ID into `list_datasets_by_theme`. The type system ensures the agent doesn't invent non-existent themes.

The Spanish catalog provides public metadata, modification dates, and publisher IDs, meaning no PII is involved. Vinkius processes these specific taxonomy requests through ephemeral sandboxes, ensuring your Pydantic schemas never leak to persistent proxy servers.

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