Bring Open Data
to Pydantic AI
Learn how to connect Ayuntamiento de Barcelona (CKAN) to Pydantic AI and start using 7 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 Ayuntamiento de Barcelona (CKAN) MCP Server?
Connect to the Ayuntamiento de Barcelona (Open Data BCN) portal and transform public data into actionable insights through natural conversation. This MCP server leverages the CKAN API to provide real-time access to Barcelona's official data repository.
What you can do
- Dataset Discovery — List all available datasets or search for specific topics like transportation, environment, or demographics using
bcn_package_search. - Metadata Inspection — Retrieve detailed metadata for specific datasets and resources to understand data structures and update frequencies.
- Deep Data Querying — Use
bcn_datastore_searchto filter records within CSV resources or execute complexbcn_datastore_search_sqlqueries for precise data extraction. - Resource Management — List all resources associated with a dataset, including download links and format specifications.
How it works
- Subscribe to this server
- Enter your Open Data BCN API Token (optional for public data, required for higher rate limits)
- Start querying Barcelona's public data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Data Analysts & Researchers — Quickly fetch and filter urban data without manual CSV downloads.
- Urban Planners — Access real-time statistics on city infrastructure and services.
- Developers — Integrate official city data into applications using SQL-like queries directly from the AI.
Built-in capabilities (7)
List datasets including their resources
Search and filter records within a specific CSV resource
The table name must be the resource_id wrapped in double quotes. Execute SQL queries directly against a resource
List all dataset names in the Open Data BCN catalogue
Search for datasets matching specific criteria
Get metadata for a specific dataset
Get metadata for a specific resource
Why Pydantic AI?
Pydantic AI validates every Ayuntamiento de Barcelona (CKAN) tool response against typed schemas, catching data inconsistencies at build time. Connect 7 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 Ayuntamiento de Barcelona (CKAN) integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Ayuntamiento de Barcelona (CKAN) connection logic from agent behavior for testable, maintainable code
Ayuntamiento de Barcelona (CKAN) in Pydantic AI
Ayuntamiento de Barcelona (CKAN) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Ayuntamiento de Barcelona (CKAN) 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 Ayuntamiento de Barcelona (CKAN) in Pydantic AI
The Ayuntamiento de Barcelona (CKAN) 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 7 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
Ayuntamiento de Barcelona (CKAN) for Pydantic AI
Every tool call from Pydantic AI to the Ayuntamiento de Barcelona (CKAN) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I perform SQL queries on Barcelona's public datasets?
Yes, you can use the bcn_datastore_search_sql tool to execute SELECT statements directly against any resource that is stored in the portal's datastore.
How do I find datasets related to a specific topic like 'transport'?
Use the bcn_package_search tool with the query parameter q set to your topic. You can also limit the number of results for faster browsing.
Is it possible to see the actual rows of a CSV file without downloading it?
Absolutely. The bcn_datastore_search tool allows you to query and preview the contents of a resource directly, including filtering and sorting options.
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 Ayuntamiento de Barcelona (CKAN) 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 →
Heymarket
9 toolsText customers from a shared business number with two-way SMS, scheduled messages, and CRM integrations for team communication.
EngageBay All-in-One CRM
10 toolsEquip your AI agent to manage contacts, track sales deals, and monitor CRM tasks via the EngageBay API.
Kontent.ai (Enterprise Headless CMS)
10 toolsManage enterprise content via Kontent.ai — create items, publish language variants, and audit content types.
Deterministic Base Converter
3 toolsEquip your AI with infinite-precision mathematical conversion between any numerical bases (2 through 36), including Binary, Hexadecimal, and Octal.