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

Q: How does OpenAI Agents SDK discover tools in the Inep Dados Abertos MCP Server?

The SDK uses the MCPServerStreamableHttp class to automatically pull the tool schema from the Vinkius endpoint. Your agent registers all 12 tools, including searchdatastoresql, without any manual mapping.

Q: Does Inep Dados Abertos support complex SQL joins when queried via OpenAI Agents SDK?

Yes, searchdatastoresql executes standard SQL queries directly on the CKAN datastore. Your agent writes joins to combine school infrastructure data with exam results.

Q: How do I handle rate limits during heavy data extraction?

Setting cacheToolsList=True in your Python code prevents redundant MCP schema lookups. For large datasets, configure your agent to paginate results using the limit parameters in searchdatastore.

Get raw Brazilian educational datasets directly into your OpenAI Agents SDK pipeline without manual downloads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inep Dados Abertos MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query ENEM and Censo Escolar with OpenAI Agents SDK

The `search_datastore_sql` tool runs raw SQL queries against INEP databases, letting your OpenAI Agents SDK agent pull targeted slices of Brazilian educational data. By querying the datastore directly, your OpenAI Agents SDK pipeline skips downloading massive INEP CSVs just to extract a single school district.

Discover new educational datasets dynamically via MCP Server

This MCP Server exposes `list_packages` and `search_packages` to let your OpenAI Agents SDK agent crawl the entire INEP catalog on demand. Dynamic discovery allows your system to identify new educational resources without hardcoded INEP endpoints.

Inspect resource structures before pulling data

Once your OpenAI Agents SDK agent finds a relevant package, it uses `get_package` to inspect the INEP metadata. The `get_resource` and `search_resources` tools provide the exact schema of any target INEP datastore to your OpenAI Agents SDK agent.

Setup guide

Set up Inep 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 Inep Dados Abertos tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Inep 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 Inep 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="Inep Dados Abertos Agent",
            instructions="You have access to Inep 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 Inep. 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 Inep 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 Inep Dados Abertos MCP in OpenAI Agents SDK

The SDK uses the `MCPServerStreamableHttp` class to automatically pull the tool schema from the Vinkius endpoint. Your agent registers all 12 tools, including `search_datastore_sql`, without any manual mapping.

You control this by defining specific agent schemas or wrapping the MCP Server connection in your Python code. By filtering the tools list before passing it to your Agent constructor, you keep execution focused.

Yes, `search_datastore_sql` executes standard SQL queries directly on the CKAN datastore. Your agent writes joins to combine school infrastructure data with exam results.

Setting `cacheToolsList=True` in your Python code prevents redundant MCP schema lookups. For large datasets, configure your agent to paginate results using the limit parameters in `search_datastore`.

Your educational query results flow directly from the INEP API through the Vinkius proxy to your local environment. No data is stored or cached on the Vinkius servers, ensuring complete transit isolation for sensitive school metrics.

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