How to Use the Focus Logística MCP in AutoGen

Q: How do AutoGen agents collaborate using Focus Logística?

You assign tools like emitcte to an AutoGen emitter agent and consultcte to an AutoGen auditor agent. The auditor agent checks the status and instructs the emitter agent to proceed with Focus Logística or correct the document.

Q: Can I use AutoGen to automate manifest closure in Focus Logística?

Yes, an AutoGen agent triggers closemdfe when another agent confirms delivery. If the Focus Logística closure fails, they discuss the error code and decide whether to retry or alert a manager.

Q: Does the Focus Logística MCP Server support AutoGen's schema format?

Yes, the McpToolAdapter converts the JSON schemas of tools like emitmdfe into the format AutoGen expects. Your AutoGen agents can call these Focus Logística tools out of the box without manual schema mapping.

Q: How do AutoGen agents handle Focus Logística document cancellations?

Your AutoGen risk agent calls cancelcte with the document key and justification. The agent then monitors the Focus Logística status to confirm the cancellation was accepted by the tax authority.

Deploy AutoGen agent teams to negotiate, emit, and audit Brazilian CT-e and MDF-e documents via Focus Logística.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Focus Logística MCP to AutoGen

Create your Vinkius account to connect Focus Logística 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 Focus Logística with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Document Auditing and Emission

The `emit_cte` and `emit_mdfe` tools are assigned to specialized AutoGen agents to separate Focus Logística drafting from validation. One AutoGen agent compiles the shipping data, while a compliance agent reviews the Focus Logística payload before execution. This MCP capability stops bad tax data before it hits Focus Logística servers. You avoid costly validation failures and potential tax fines through automated AutoGen team review.

Collaborative Manifest Closure and Verification

The `close_mdfe` and `consult_mdfe` tools allow your AutoGen agents to coordinate the end-of-transit workflow. An AutoGen tracking agent monitors the progress, and a logistics agent closes the Focus Logística manifest once delivery is verified. If the Focus Logística closure fails, the AutoGen agents debate the resolution. They check the Focus Logística status, pull the logs, and determine whether to retry or escalate.

Automated Error Resolution via MCP Server Tools

The `cancel_cte` tool is managed by a dedicated risk-mitigation agent in your AutoGen network. When an emission error is detected, this agent coordinates with other AutoGen agents to cancel the incorrect Focus Logística document. The AutoGen agents negotiate the cancellation window. They ensure the Focus Logística cancellation occurs within the legal timeframe allowed by Brazilian tax authorities.

Setup guide

Set up Focus Logística 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 Focus Logística 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="Focus Logística_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Focus Logística 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="Focus Logística_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Focus Logística 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 Focus NFe. 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 Focus Logística 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 Focus Logística MCP in AutoGen

You assign tools like `emit_cte` to an AutoGen emitter agent and `consult_cte` to an AutoGen auditor agent. The auditor agent checks the status and instructs the emitter agent to proceed with Focus Logística or correct the document.

Yes, an AutoGen agent triggers `close_mdfe` when another agent confirms delivery. If the Focus Logística closure fails, they discuss the error code and decide whether to retry or alert a manager.

Yes, the `McpToolAdapter` converts the JSON schemas of tools like `emit_mdfe` into the format AutoGen expects. Your AutoGen agents can call these Focus Logística tools out of the box without manual schema mapping.

Your AutoGen risk agent calls `cancel_cte` with the document key and justification. The agent then monitors the Focus Logística status to confirm the cancellation was accepted by the tax authority.

Your CT-e and MDF-e payload data stays inside your private AutoGen execution environment. The MCP Server acts as an ephemeral gateway, passing data directly to the Focus NFe API without caching or logging your cargo details.

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