How to Use the Acre Dados Abertos MCP in OpenAI Agents SDK

Q: How do I search Acre Dados Abertos for specific records using the OpenAI Agents SDK?

Your agent uses the searchdatastore tool. Just pass it the resource ID and your search query. The OpenAI Agents SDK handles the call and returns the results directly to your agent's context.

Q: Can my agent list all available datasets from Acre Dados Abertos with the OpenAI Agents SDK?

Yes, it uses the listpackages tool for that. It returns a complete list of all dataset names available through the portal. Your agent can then iterate through them or use other tools to get more details.

Q: What's the best way to find datasets from a specific organization in Acre Dados Abertos using my OpenAI agent?

Have your agent call listorganizations to get a list of all publishing bodies. Then, it can use an organization's ID with searchpackages to filter for datasets published only by that specific entity.

Q: Is there a way to group related datasets together?

The listgroups tool shows you all the thematic categories, like 'Education' or 'Environment'. Your agent can then use getgroup to see all the datasets that fall under a specific theme.

Build production agents that query Brazilian public data with the safety and tracing of the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Acre Dados Abertos MCP to OpenAI Agents SDK

Create your Vinkius account to connect Acre Dados Abertos 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 Acre Dados Abertos with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Acre's Datasets from Your Agent

Your agent can find specific datasets or even individual records inside them. Use `search_packages` to locate datasets about public health, for example, then dive into the data with `search_datastore`. This is where the OpenAI Agents SDK really shines. Its built-in guardrails mean you can let your agent search without worrying it'll go off the rails. Every action is validated before it runs, and you get a full trace in your OpenAI dashboard to see exactly what happened.

Explore Data Structure with Your MCP Server

This MCP Server lets your agent map out the entire Acre public data catalog. It can start by listing all available datasets with `list_packages`, then organize them by topic using `list_groups` or by the publishing body with `list_organizations`. This setup is perfect for specialized agent systems. One agent could be responsible for mapping the data landscape, then hand off specific dataset IDs to another agent for deep analysis. The OpenAI Agents SDK makes these handoffs simple and traceable.

Get Granular Metadata on Demand

Once your agent has an ID, it can pull detailed metadata. Use `get_package` to get the full story on a dataset, or `get_resource` to understand the format and location of a specific file, like a CSV or a shapefile. Because these tools are exposed through an MCP server, your agent auto-discovers them with no extra configuration. Set `cacheToolsList=True` in the setup and you're ready for production traffic. It just works.

Setup guide

Set up Acre Dados Abertos 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 Acre Dados Abertos tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Acre Dados Abertos 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="Acre Dados Abertos Agent",
            instructions="You have access to Acre Dados Abertos 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 Acre Dados Abertos. 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 Acre Dados Abertos 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 Acre Dados Abertos MCP in OpenAI Agents SDK

Your agent uses the `search_datastore` tool. Just pass it the resource ID and your search query. The OpenAI Agents SDK handles the call and returns the results directly to your agent's context.

Yes, it uses the `list_packages` tool for that. It returns a complete list of all dataset names available through the portal. Your agent can then iterate through them or use other tools to get more details.

Have your agent call `list_organizations` to get a list of all publishing bodies. Then, it can use an organization's ID with `search_packages` to filter for datasets published only by that specific entity.

The `list_groups` tool shows you all the thematic categories, like 'Education' or 'Environment'. Your agent can then use `get_group` to see all the datasets that fall under a specific theme.

This server only interacts with public, open-source government data from the State of Acre. No private or user-specific information is ever accessed. Vinkius isolates each request in an ephemeral sandbox, and your connection is secured via a single endpoint token, so your credentials are never exposed to the server itself.

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