How to Use the Inep Dados Abertos MCP in AutoGen

Q: How do AutoGen agents collaborate using the Inep Dados Abertos MCP Server?

One agent can search for datasets using searchpackages while another agent runs SQL queries using searchdatastoresql. They pass the results back and forth to build a unified report.

Q: How do I register the Inep Dados Abertos MCP Server tools with my AutoGen agent?

You use the mcpservertools adapter to load the tools and pass them to your AssistantAgent. The adapter automatically maps the 12 INEP tools to the agent's schema.

Build multi-agent AutoGen teams to analyze and debate Brazilian educational data from INEP.

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 AutoGen

Create your Vinkius account to connect Inep Dados Abertos to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Multi-Agent SQL Analysis

`search_datastore_sql` allows your AutoGen data analyst agent to run complex queries using this MCP server while a critic agent reviews the output. The analyst agent writes the SQL to pull ENEM or Censo Escolar data, and the critic verifies the logic before finalizing the report. Working in tandem prevents single-agent errors when handling complex public datasets. If the query fails, the agents negotiate a fix. The analyst agent can call `search_resources` to verify the column names and modify the SQL syntax without requiring human intervention.

Automate Catalog Discovery with this MCP Server

`list_packages` and `search_packages` enable your AutoGen research agent to scour the INEP catalog for new datasets. The research agent identifies relevant packages and passes them to a processing agent. Keeping your multi-agent system organized in this manner avoids redundant API calls. The processing agent then uses `get_package` to inspect the dataset contents. If the package contains multiple resources, the agent coordinates with other team members to decide which files to analyze first.

Map Administrative Structures in AutoGen

`list_organizations` and `get_organization` let your AutoGen agents identify which government departments published specific educational metrics. A compliance agent can use this information to verify the source of the data before it is used in official reports. This ensures your automated workflows maintain high standards of data provenance. Your agents can also query `list_groups` to understand the thematic division of the datasets. Routing specific tasks to specialized sub-agents based on their expertise becomes straightforward when you have the group metadata.

Setup guide

Set up Inep Dados Abertos MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Inep Dados Abertos tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Inep Dados Abertos_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Inep Dados Abertos data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Inep Dados Abertos_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Inep Dados Abertos data")
    print(result.messages[-1].content)

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 AutoGen

One agent can search for datasets using `search_packages` while another agent runs SQL queries using `search_datastore_sql`. They pass the results back and forth to build a unified report.

Yes, your critic agent can inspect the SQL syntax generated for `search_datastore_sql` and compare it against schemas retrieved via `get_resource`. This ensures the queries are accurate before execution.

You use the `mcp_server_tools` adapter to load the tools and pass them to your AssistantAgent. The adapter automatically maps the 12 INEP tools to the agent's schema.

Yes, you can configure a coordinator agent to manage the frequency of tool calls. If a query to `search_datastore` slows down, the agent can pause or queue subsequent requests.

All tools query public, de-identified datasets hosted directly by INEP. No private student details are accessed, and the local sandbox environment ensures that your agent configurations and API tokens remain private.

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