Bring Open Data
to Pydantic AI
Learn how to connect Dades Obertes Catalunya to Pydantic AI and start using 2 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 Dades Obertes Catalunya MCP Server?
Unlock the power of Dades Obertes Catalunya, the official open data platform of the Government of Catalonia. This MCP server allows your AI agent to browse thousands of public datasets and perform complex queries through natural conversation.
What you can do
- Catalog Discovery — Search for datasets by keywords, categories, or tags to find relevant public information using the
search_catalogtool. - Advanced Querying — Use SoQL (Socrata Query Language) via
query_datasetto filter, select specific columns, and sort data from any dataset using its 4x4 identifier. - Data Analysis — Group results and perform full-text searches across entire datasets to extract insights on health, transport, economy, and more.
- Pagination & Limits — Efficiently handle large datasets with built-in support for limits and offsets to browse records systematically.
How it works
- Subscribe to this server
- (Optional) Enter your Socrata App Token for higher rate limits
- Start querying Catalan public data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Data Analysts — quickly pull public statistics into your workflow without manual CSV downloads
- Researchers — find and cross-reference government data on demographics, environment, or urban planning
- Developers — test data queries and explore API structures directly through natural language
Built-in capabilities (2)
g., abcd-1234). Supports SoQL parameters like $select, $where, $limit. Query a specific dataset using SoQL parameters
Returns dataset identifiers needed for the query_dataset tool. Search the Dades Obertes Catalunya catalog for datasets
Why Pydantic AI?
Pydantic AI validates every Dades Obertes Catalunya tool response against typed schemas, catching data inconsistencies at build time. Connect 2 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 Dades Obertes Catalunya integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Dades Obertes Catalunya connection logic from agent behavior for testable, maintainable code
Dades Obertes Catalunya in Pydantic AI
Dades Obertes Catalunya and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Dades Obertes Catalunya 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 Dades Obertes Catalunya in Pydantic AI
The Dades Obertes Catalunya 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 2 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
Dades Obertes Catalunya for Pydantic AI
Every tool call from Pydantic AI to the Dades Obertes Catalunya MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find the unique identifier for a specific dataset?
Use the search_catalog tool with a descriptive query. The response will include the 4x4 alphanumeric ID (e.g., 'abcd-1234') which you can then use with the query_dataset tool.
Can I filter data by specific values like a city or a date range?
Yes! When using query_dataset, use the $where parameter to apply SoQL filters. For example, $where: "poblacio > 5000" or $where: "comarca = 'Barcelonès'".
Is a Socrata App Token mandatory to use this server?
No, it is optional. However, providing a DADES_APP_TOKEN allows for higher rate limits and prevents throttling during intensive data exploration.
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 Dades Obertes Catalunya 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 →
Canvas LMS
45 toolsManage Canvas LMS courses, assignments, and users directly through your AI agent — streamline educational workflows and administrative tasks.
Postmark
11 toolsAutomate transactional email delivery via Postmark — manage servers, templates, and bounces directly from any AI agent.
Prismic
10 toolsQuery and manage your Prismic headless CMS content — search documents, list custom types, and retrieve specific content directly from any AI agent.
Maxar (Satellite Imagery)
4 toolsAccess high-resolution satellite imagery and geospatial data from Maxar — search discovery catalogs, order data products, and retrieve streaming endpoints.