How to Use the Cuiabá Transparency MCP in AutoGen

Q: How do I load Cuiabá Transparency into AutoGen?

Install the autogen-extmcp package. Use the mcpservertools method with your Streamable HTTP parameters to fetch the tool definitions, then pass them straight to your AssistantAgent.

Equip your AutoGen multi-agent debates with live municipal data from Cuiabá.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cuiabá Transparency MCP to AutoGen

Create your Vinkius account to connect Cuiabá Transparency 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 Cuiabá Transparency with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cuiabá Transparency MCP Server Debates

AutoGen shines when agents challenge each other. You can assign one agent the role of auditor, tasked with running `list_budget` to find allocated funds. A second analyst agent then runs `list_expenses` to verify how that money actually moved. They debate the variance. If the numbers don't match, the agents discuss the discrepancy in real-time until they reach a consensus. You watch the logic unfold step-by-step in the terminal.

Cross-Checking Public Tenders

Evaluating public contracts requires multiple perspectives. A legal agent checks `list_contracts` for compliance flags, while a financial agent queries `list_personnel` to ensure no conflict of interest exists between contractors and city staff. The MCP server adapter handles all schema conversions automatically. Your agents read the returned JSON natively, allowing them to focus entirely on the negotiation and analysis rather than parsing data structures.

Consensus-Driven Revenue Analysis

Building a municipal financial report isn't a straight line. Your AutoGen setup can trigger `list_revenues` to pull tax collection data. A skeptical agent might flag anomalies and request a re-query with different parameters. This back-and-forth produces highly accurate summaries. Instead of accepting the first output blindly, the system iterates on the MCP tool data until all participating agents agree on the final conclusion.

Setup guide

Set up Cuiabá Transparency 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 Cuiabá Transparency 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="Cuiabá Transparency_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cuiabá Transparency 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="Cuiabá Transparency_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cuiabá Transparency 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 Cuiabá Transparency 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 Cuiabá Transparency 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 Cuiabá Transparency MCP in AutoGen

Install the autogen-ext[mcp] package. Use the mcp_server_tools method with your Streamable HTTP parameters to fetch the tool definitions, then pass them straight to your AssistantAgent.

Any agent equipped with the tool list can invoke the endpoints. They will share the returned data in the group chat, allowing other agents to analyze the results.

The built-in adapter automatically translates the tool specifications into the format the framework requires. You skip manual configuration and go straight to agent deployment.

Yes, you instantiate the connection using StreamableHttpServerParams. This allows your local agents to communicate with hosted MCP endpoints over standard HTTP.

Vinkius runs the endpoint inside an isolated V8 sandbox. When your agents pull public tender details, the environment exists only for the duration of that specific request. Your token authorizes the connection, and the container vanishes immediately after returning the payload.

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