How to Use the Aragón Open Data MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle large tables returned by Aragón Open Data?

The previewdata tool caps the default response at 1,000 records to keep your agent from hitting token limits. Your SDK can then process these rows in chunks or pass them to a specialized analysis agent.

Get Aragón public data directly into your OpenAI Agents SDK production workflows with this zero-config MCP server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Aragón Open Data to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Aragon CKAN datasets with OpenAI Agents SDK

The `search_datasets` tool exposes the entire Government of Aragón public catalog directly to your OpenAI agent. Your agent can run deep searches, inspect specific metadata using `get_dataset`, and even pinpoint publisher details using `get_organization` without writing manual API wrappers. Because you are building with the OpenAI Agents SDK, you can set up guardrails that intercept these calls. This keeps your production agent from pulling massive payloads or querying invalid catalog paths before the execution phase starts.

Preview raw data views using this MCP Server

The `preview_data` tool grabs the first 1,000 records of any Aragón public data view so your agent can inspect the structure. To make this work, the agent first calls `list_views` to find active endpoints, then uses `show_columns` to understand the schema before pulling the actual rows. Your OpenAI Agents SDK setup handles this multi-step discovery process through autonomous agent handoffs. You can have a specialized data analyst agent preview the rows, clean the schema, and pass the structured results to your main agent.

Execute complex SPARQL queries safely

The `query_sparql` tool runs direct semantic queries against Aragopedia, EI2A, and other regional ontologies. Your agent can pull relationships and structured data directly into its context window by calling this endpoint with custom SPARQL code. Using the OpenAI dashboard, you get complete tracing of every single SPARQL query. You see exactly what your agent asked, what the server returned, and how much context was consumed in the process.

Setup guide

Set up Aragón Open Data MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Aragón Open Data tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Aragón Open Data tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Aragón Open Data tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Aragón Open Data Agent",
            instructions="You have access to Aragón Open Data tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install openai-agents and initialize MCPServerStreamableHttp pointing to the Vinkius URL. Pass this server instance directly to your agent constructor to let it discover tools like list_datasets.

Yes, you can control tool access at the SDK layer. If you only want your agent to read metadata, you can expose list_groups while blocking tools that preview raw data.

The preview_data tool caps the default response at 1,000 records to keep your agent from hitting token limits. Your SDK can then process these rows in chunks or pass them to a specialized analysis agent.

Set cacheToolsList=True in your OpenAI server parameters. This keeps the agent from repeatedly querying the server for tool definitions like newest_datasets or most_downloaded_datasets.

The Aragón Open Data MCP server only pulls public CKAN catalog records and SPARQL views. All data passes through Vinkius's secure, ephemeral V8 sandboxes, meaning your queried Aragon public data is never stored or used to train models.

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