Bring Open Data
to Pydantic AI
Learn how to connect Datos.gob.es (Catálogo Nacional) to Pydantic AI and start using 22 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Datos.gob.es (Catálogo Nacional) MCP Server?
Connect to the official Datos.gob.es API to explore Spain's vast repository of public sector information. This MCP server allows AI agents to query, filter, and analyze thousands of datasets from national, regional, and local administrations.
What you can do
- Dataset Discovery — Search for specific datasets by title or browse the entire catalog with advanced pagination and sorting.
- Advanced Filtering — Narrow down results by publisher ID, specific themes (e.g., health, economy), or file formats like CSV, JSON, and RDF.
- Geographic Analysis — Filter data by spatial scope, including provinces, regions, or specific administrative levels.
- Metadata Inspection — Retrieve detailed metadata for any dataset, including its distributions, update frequency, and issuing body.
- Public Sector Mapping — List and inspect public sector organizations, provinces, and regions involved in the open data ecosystem.
How it works
- Subscribe to this server
- The server connects to the public Datos.gob.es API
- Start querying Spanish public data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Data Analysts — quickly find and inspect public datasets for research and reporting without manual browsing.
- Developers — identify API endpoints and data formats for integration into applications.
- Policy Researchers — track public sector transparency and data availability across different Spanish regions.
Built-in capabilities (22)
Get country-level information for Spain
Get a specific dataset by its URI identifier
g., Madrid). Get a specific province by ID
g., comercio). Get a specific primary sector by ID
g., Comunidad-Madrid). Get a specific Autonomous Community (Region) by ID
gob.es catalog. Get all datasets from the catalog
Filter datasets by modification date range
g., csv). Filter datasets by format
Filter datasets by keyword
g., A16003011). Filter datasets by publisher ID
g., word1=Autonomia, word2=Pais-Vasco). Filter datasets by geographic scope
g., hacienda). Filter datasets by theme/category
Get all data distributions
Get distributions by dataset ID
g., csv). Filter distributions by format
Get all provinces
Get the taxonomy of primary sectors
Get all publishers in the catalog
Get all Autonomous Communities (Regions)
Get all geographic coverage options
Get all categories/themes
Search datasets by title
Why Pydantic AI?
Pydantic AI validates every Datos.gob.es (Catálogo Nacional) tool response against typed schemas, catching data inconsistencies at build time. Connect 22 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Datos.gob.es (Catálogo Nacional) integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Datos.gob.es (Catálogo Nacional) connection logic from agent behavior for testable, maintainable code
Datos.gob.es (Catálogo Nacional) in Pydantic AI
Datos.gob.es (Catálogo Nacional) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Datos.gob.es (Catálogo Nacional) to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Datos.gob.es (Catálogo Nacional) in Pydantic AI
The Datos.gob.es (Catálogo Nacional) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 22 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Datos.gob.es (Catálogo Nacional) for Pydantic AI
Every tool call from Pydantic AI to the Datos.gob.es (Catálogo Nacional) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I search for datasets containing a specific word in the title?
Use the search_datasets_by_title tool. Provide the string you are looking for in the title parameter, and the agent will return all matching datasets from the national catalog.
Is it possible to filter datasets by a specific file format like CSV or JSON?
Yes! Use the list_datasets_by_format tool and specify the format (e.g., 'csv', 'json', 'xlsx'). This will retrieve only the datasets that offer distributions in that format.
Can I find datasets belonging to a specific category like 'Health' or 'Environment'?
Absolutely. Use the list_datasets_by_theme tool with the corresponding theme ID. You can first use list_themes to see all available categories in the catalog.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Datos.gob.es (Catálogo Nacional) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
arXiv Alternative
4 toolsAccess millions of scientific papers from arXiv — search by author, category, or keyword and fetch metadata directly from the open-access archive.
Steam
10 toolsAccess Steam gaming data — player profiles, owned games, achievements, and stats via AI.
MediaSilo
10 toolsVideo collaboration and asset management via MediaSilo — manage projects, assets, and Quicklinks.
Zoho CRM Sales
10 toolsDeep deal management with quotes, products, sales orders, and invoices — complete sales cycle in Zoho CRM.