How to Use the Aragón Open Data MCP in Pydantic AI

Q: How do I set up the Aragón Open Data MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp and initialize MCPToolset pointing to the Vinkius server URL. Pass this toolset into your Agent constructor to let it run tools like listdatasets.

Q: How do I validate the most popular datasets from Aragon?

Use the mostdownloadeddatasets tool. Pydantic AI will validate the list of popular packages, ensuring fields like download counts and package IDs match your expected integer and string types.

Run type-safe queries against Aragón public datasets using this type-safe MCP server with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aragón Open Data MCP to Pydantic AI

Create your Vinkius account to connect Aragón Open Data 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 Aragón Open Data with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Aragon CKAN schemas at runtime with Pydantic AI

The `get_dataset` tool pulls public metadata from the Aragon catalog directly into your runtime environment. Instead of hoping the API structure hasn't changed, Pydantic AI validates the returned JSON against your strict schemas immediately. If the catalog structure changes, your agent fails loudly with a validation error rather than passing corrupt data down your pipeline. This guarantees your production systems only process clean Aragon metadata.

Type-safe raw data previewing using this MCP Server

The `preview_data` tool fetches up to 1,000 records from active Aragon public views. Your agent first calls `show_columns` to inspect the field types, allowing you to dynamically construct Pydantic models for validation. This setup prevents silent failures when reading public data tables. Because Pydantic AI enforces strict types, any unexpected null values or broken schemas are caught before they reach your analysis models.

Query complex SPARQL data without silent corruption

The `query_sparql` tool lets your agent run advanced queries against regional ontologies like Aragopedia. Since SPARQL results can be deeply nested, validating them at runtime is critical for system stability. Using this framework, your agent parses the SPARQL response directly into typed Python objects. You get complete confidence that every node and relation returned by the Aragon server matches your exact schema.

Setup guide

Set up Aragón Open Data 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": {
        "aragon-open-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Aragón Open Data tools.",
)

result = await agent.run("List recent Aragón Open Data 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 Aragón Open Data. 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 Aragón Open Data 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 Aragón Open Data MCP in Pydantic AI

Install pydantic-ai-slim[mcp] and initialize MCPToolset pointing to the Vinkius server URL. Pass this toolset into your Agent constructor to let it run tools like list_datasets.

Your agent will raise a validation error instantly. This prevents the agent from hallucinating or processing corrupt catalog data from tools like get_organization.

The server must run externally on Vinkius, but your Pydantic AI agent connects to it securely via HTTP or SSE transports using the unified MCPToolset class.

Use the most_downloaded_datasets tool. Pydantic AI will validate the list of popular packages, ensuring fields like download counts and package IDs match your expected integer and string types.

The Aragón Open Data MCP server only handles public CKAN registry records and SPARQL views. All traffic runs through Vinkius's isolated, ephemeral V8 sandboxes, meaning your queried records are never cached or logged on Vinkius servers.

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