How to Use the Ayuntamiento de Barcelona (CKAN) MCP in Pydantic AI

Q: What happens if the Ayuntamiento de Barcelona (CKAN) API changes and my Pydantic AI agent gets bad data?

Your agent will fail loudly with a ValidationError. Pydantic AI validates every response from the MCP server against your models, so any unexpected change in the data structure from the source API is caught immediately. You won't have to deal with silent data corruption.

Q: How do I define the data structures for the Ayuntamiento de Barcelona (CKAN) tools in Pydantic AI?

You don't have to for the tool's input arguments; pydantic-ai infers them from the MCP Server's OpenAPI schema. For the output, you can define your own Pydantic models to validate the data returned by tools like bcndatastoresearch.

Q: Which tool should I use for complex queries, bcndatastoresearch or bcndatastoresearchsql?

Use bcndatastoresearchsql for complex queries involving aggregations or joins. Just be aware that the output structure will be dynamic. For simpler, filter-based lookups where you want strong type safety on the results, bcndatastoresearch combined with a Pydantic model is the better choice.

Get type-safe, validated access to Barcelona's open data in Python with Pydantic AI. No more silent data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ayuntamiento de Barcelona (CKAN) MCP to Pydantic AI

Create your Vinkius account to connect Ayuntamiento de Barcelona (CKAN) 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 Ayuntamiento de Barcelona (CKAN) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Schema-Validated Metadata

Use the `bcn_package_show` and `bcn_resource_show` tools to fetch the schema and metadata for any dataset. Your agent can inspect available fields, their types, and descriptions before attempting a query. With Pydantic AI, the JSON response from this MCP server is automatically parsed and validated against Pydantic models. If the API ever returns an unexpected structure, your code raises a `ValidationError` immediately. This guarantees the metadata your agent is working with is always correct.

Run Type-Safe Data Searches

The `bcn_datastore_search` tool lets your agent search for records within a specific resource. It's great for pulling rows that match certain criteria from one of Barcelona's many public CSVs. The real benefit with Pydantic AI is that the results are also validated. You define a Pydantic model for the expected row structure, and the framework ensures every record returned from the MCP Server conforms to it. You get clean, predictable data objects every time.

Connect to Any LLM with Pydantic AI

Integrating this server is done by creating an `MCPToolset` with your Vinkius URL and passing it to your Pydantic AI `Agent`. It's a single line of code to give your agent access to Barcelona's entire open data catalog. Since Pydantic AI is model-agnostic, you can use these tools with OpenAI, Anthropic, Gemini, or even a local model. The data validation works the same way regardless of the LLM you choose, ensuring consistent and reliable behavior.

Setup guide

Set up Ayuntamiento de Barcelona (CKAN) 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": {
        "ayuntamiento-de-barcelona-ckan-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Ayuntamiento de Barcelona (CKAN) tools.",
)

result = await agent.run("List recent Ayuntamiento de Barcelona (CKAN) 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 Open Data BCN. 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 Ayuntamiento de Barcelona (CKAN) 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 Ayuntamiento de Barcelona (CKAN) MCP in Pydantic AI

Your agent will fail loudly with a `ValidationError`. Pydantic AI validates every response from the MCP server against your models, so any unexpected change in the data structure from the source API is caught immediately. You won't have to deal with silent data corruption.

You don't have to for the tool's input arguments; `pydantic-ai` infers them from the MCP Server's OpenAPI schema. For the output, you can define your own Pydantic models to validate the data returned by tools like `bcn_datastore_search`.

Yes. Pydantic AI is model-agnostic, so you can connect it to any LLM, whether it's hosted by a major provider or running on your own machine. The tool-use and validation logic remains exactly the same.

Use `bcn_datastore_search_sql` for complex queries involving aggregations or joins. Just be aware that the output structure will be dynamic. For simpler, filter-based lookups where you want strong type safety on the results, `bcn_datastore_search` combined with a Pydantic model is the better choice.

When your agent queries for public statistics or urban datasets from Barcelona's portal, the requests pass through Vinkius's secure system. Each operation runs in an isolated sandbox that is destroyed after use. Authentication is handled via a single, revocable token, protecting your agent's credentials.

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