How to Use the Minas Gerais (Estado) MCP in AutoGen

Q: How do I register the Minas Gerais (Estado) MCP Server with AutoGen agents?

You use the mcpservertools adapter with the server's HTTP URL. This automatically maps tools like searchpackages and getpackage into schemas that your AutoGen AssistantAgent can understand and execute.

Q: Can AutoGen agents collaborate to find Minas Gerais (Estado) resources?

Yes, a coordinator agent can direct a search agent to run searchresources for specific files. Once the search agent returns the metadata, a data analyst agent can evaluate the file parameters retrieved from the state's portal.

Q: Can an agent list all available tags on the state portal?

Yes, the agent can call listtags to get the complete list of taxonomy terms. This helps the team refine their search queries before calling broader search tools.

Deploy AutoGen multi-agent teams that debate and analyze public datasets retrieved from the Minas Gerais (Estado) portal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Minas Gerais (Estado) MCP to AutoGen

Create your Vinkius account to connect Minas Gerais (Estado) 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 Minas Gerais (Estado) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debates over Minas Gerais (Estado) data

Set up an AutoGen conversation where one agent acts as a data retriever and another as a validator. The retriever uses `search_packages` to find economic datasets from Minas Gerais (Estado). The validator agent then uses `get_package` to check the update frequency and metadata completeness before accepting the file. This collaborative approach ensures that your system doesn't rely on the first random file it finds. The agents discuss whether the dataset is relevant to the user's request, using the state's actual metadata as the source of truth.

Automate state resource audits with AutoGen

Let your AutoGen agents run automated audits on state files. An agent can call `list_packages` to get the list of active datasets, then loop through them using `get_resource` to find broken or outdated download links on the Minas Gerais (Estado) portal. Another agent can write a report summarizing which state departments have the most reliable data. Because AutoGen handles multi-step conversations, this entire audit happens autonomously without human intervention.

Coordinate complex queries via MCP Server tools

When a query requires combining data from multiple state departments, AutoGen agents can divide and conquer. One agent queries the health department using `get_organization`, while another queries the education department. They share their findings to build a unified picture. They use tools like `list_groups` and `search_resources` to locate the exact CSV files needed. This coordination makes it possible to answer complex cross-departmental questions about Minas Gerais (Estado) public policy.

Setup guide

Set up Minas Gerais (Estado) 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 Minas Gerais (Estado) 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="Minas Gerais (Estado)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Minas Gerais (Estado) 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="Minas Gerais (Estado)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Minas Gerais (Estado) 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 Minas Gerais 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 Minas Gerais (Estado) 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 Minas Gerais (Estado) MCP in AutoGen

You use the `mcp_server_tools` adapter with the server's HTTP URL. This automatically maps tools like `search_packages` and `get_package` into schemas that your AutoGen `AssistantAgent` can understand and execute.

Yes, a coordinator agent can direct a search agent to run `search_resources` for specific files. Once the search agent returns the metadata, a data analyst agent can evaluate the file parameters retrieved from the state's portal.

This MCP Server supports both stdio and Streamable HTTP transports. When configuring your AutoGen environment, you can point the `StreamableHttpServerParams` directly to the hosted Vinkius endpoint for Minas Gerais (Estado).

Yes, the agent can call `list_tags` to get the complete list of taxonomy terms. This helps the team refine their search queries before calling broader search tools.

No, your agent prompts and internal multi-agent chats are kept entirely private. Only the specific parameters generated for tools like `get_package` or `list_organizations` are sent to the state's CKAN API, with Vinkius managing the MCP connection securely.

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