How to Use the Datos Abiertos Castilla-La Mancha MCP in Pydantic AI

Q: How do I register Datos Abiertos Castilla-La Mancha with Pydantic AI?

You instantiate MCPToolset with the Vinkius HTTP endpoint and pass it to your agent's MCP server configuration. The framework automatically imports all five tools and validates their inputs and outputs at runtime. This ensures your agent only works with correctly structured data.

Q: Can I run complex filters on Datos Abiertos Castilla-La Mancha tables using Pydantic AI?

Yes, you can use the searchdatastore tool to execute precise queries against Castilla-La Mancha's tabular databases. The framework validates the returned rows against your models to ensure safe data handling. This guarantees your agent only acts on clean, validated records.

Validate Castilla-La Mancha open data at runtime with type-safe Pydantic AI agent tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datos Abiertos Castilla-La Mancha MCP to Pydantic AI

Create your Vinkius account to connect Datos Abiertos Castilla-La Mancha 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 Abiertos Castilla-La Mancha with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe discovery of Spanish public data

The `list_datasets` tool fetches the entire active dataset directory from Castilla-La Mancha's open data portal. Your agent pairs this with `list_tags` to classify datasets by regional topics, ensuring every tag matches your strict validation rules. Because Pydantic AI enforces type safety at runtime, you never have to worry about null values or missing fields breaking your application. The incoming JSON structure is validated against Python models before your agent even processes it.

Validate metadata schemas using this MCP Server

This MCP Server uses `get_dataset` to retrieve exact schema layouts and update frequencies from the CKAN portal. Your agent then invokes `get_resource` to extract individual file locations, validating that the URLs and file sizes conform to your expected types. If the Spanish government portal returns an unexpected data type, your application fails loudly and immediately. This prevents corrupted metadata from silently polluting your downstream data pipelines.

Type-safe database querying

The `search_datastore` tool allows your agent to run precise queries against Castilla-La Mancha's active database tables. The returned rows are instantly parsed into structured Pydantic models, verifying the integrity of every single field. This setup lets your agent run complex data analysis without risking type errors. You get clean, validated regional data ready for production use cases.

Setup guide

Set up Datos Abiertos Castilla-La Mancha 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": {
        "datos-abiertos-castilla-la-mancha-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Datos Abiertos Castilla-La Mancha tools.",
)

result = await agent.run("List recent Datos Abiertos Castilla-La Mancha 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 Abiertos Castilla-La Mancha. 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 Abiertos Castilla-La Mancha 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 Abiertos Castilla-La Mancha MCP in Pydantic AI

You instantiate `MCPToolset` with the Vinkius HTTP endpoint and pass it to your agent's MCP server configuration. The framework automatically imports all five tools and validates their inputs and outputs at runtime. This ensures your agent only works with correctly structured data.

The framework will raise a validation error immediately if a field in `get_dataset` or `get_resource` does not match the expected schema. This prevents your agent from hallucinating or processing broken data. You can catch these errors gracefully to trigger fallback routines.

Yes, you can use the `search_datastore` tool to execute precise queries against Castilla-La Mancha's tabular databases. The framework validates the returned rows against your models to ensure safe data handling. This guarantees your agent only acts on clean, validated records.

No, Vinkius hosts and manages the server externally in a secure sandbox. Your Pydantic AI agent connects directly to the hosted HTTP endpoint. You do not need to manage any local processes or dependencies.

This integration only transmits public Castilla-La Mancha dataset queries and metadata. No private application schemas, model weights, or API keys are ever sent to the public portal. All communication is encrypted and runs inside isolated, ephemeral Vinkius MCP containers.

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