How to Use the Campinas Open Data MCP in AutoGen

Q: How can my AutoGen agents work together to explore data from Campinas Open Data?

Assign one agent to act as a 'Lister' using listpackages to get a complete inventory. Then have a second 'Analyst' agent iterate through that list, using getpackage to pull metadata for each one and report its findings.

Q: Can an AutoGen agent search for organizations in Campinas Open Data and have another agent verify it?

Yes, that's a perfect use case. One agent can use searchpackages with an organization's name. A 'Critic' agent can then review the results and use getpackage to confirm the organization listed in the metadata matches the query.

Q: If I want to find all datasets tagged 'transportation' in Campinas Open Data with AutoGen, how would that work?

A simple setup is a single AssistantAgent armed with the searchpackages tool. It will take your request, call the tool with the 'transportation' tag, and return the list of matching datasets directly to you or another agent.

Q: What's the difference between listgroups and listtags?

listgroups returns broad, official categories like 'Health' or 'Education'. listtags gives you more specific, granular keywords. Your agents can use both to get a full picture of the data before searching.

Let specialist AutoGen agents debate and analyze Campinas public data to find the best answers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Campinas Open Data MCP to AutoGen

Create your Vinkius account to connect Campinas Open Data 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 Campinas Open Data with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up an Agent Debate

Create a team of agents that challenge each other. A "Researcher" agent can use `search_packages` to find all datasets tagged 'finance'. A "Validator" agent then takes that list, uses `get_package` on each one, and flags any that haven't been updated in the last year. This isn't a simple pipeline; it's a conversation. One agent's output is critiqued by another, which produces a more reliable and vetted result than a single agent could alone. They work together to refine the answer.

Assign Roles for Complex Tasks

Divide the labor for ambiguous problems. An "Explorer" agent can use `list_groups` and `list_tags` to map out the data landscape. A "Planner" agent then uses that map to decide which specific datasets to investigate based on your goal. Finally, a "Reporter" agent can fetch resource details with `get_resource` and summarize the findings. This multi-agent approach is ideal for tasks where the right path isn't obvious. Your team of agents can navigate the Campinas data portal conversationally, figuring out the best strategy as they go.

Get Consensus-Driven MCP Server Results

The final answer is an agreement, not just a raw API response. Ask for "the most important public health dataset," and one agent might argue for the one with the most resources, found via `search_resources`. Another might argue for the most recently updated one, checked with `get_package`. They debate until they reach a consensus. The output you get is a conclusion that your team of agents has already vetted. This MCP server provides the raw facts they use to argue their points and reach a sound decision.

Setup guide

Set up Campinas Open Data 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 Campinas Open Data 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="Campinas Open Data_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Campinas Open Data 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="Campinas Open Data_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Campinas Open Data 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 Campinas Open Data Portal. 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 Campinas 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 Campinas Open Data MCP in AutoGen

Assign one agent to act as a 'Lister' using `list_packages` to get a complete inventory. Then have a second 'Analyst' agent iterate through that list, using `get_package` to pull metadata for each one and report its findings.

Yes, that's a perfect use case. One agent can use `search_packages` with an organization's name. A 'Critic' agent can then review the results and use `get_package` to confirm the organization listed in the metadata matches the query.

A simple setup is a single `AssistantAgent` armed with the `search_packages` tool. It will take your request, call the tool with the 'transportation' tag, and return the list of matching datasets directly to you or another agent.

`list_groups` returns broad, official categories like 'Health' or 'Education'. `list_tags` gives you more specific, granular keywords. Your agents can use both to get a full picture of the data before searching.

Your agents only interact with publicly available data from the city of Campinas. Your connection is managed by Vinkius through a single, secure endpoint token, and the MCP server runs in a temporary, isolated environment that protects your system.

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