How to Use the Focus Logística MCP in OpenAI Agents SDK

Q: How do I handle SEFAZ timeout errors using Focus Logística with OpenAI Agents SDK?

If SEFAZ times out during emitcte, configure your OpenAI Agents SDK agent to run consultcte before attempting a retry. This prevents duplicate document submissions and keeps your tax records clean.

Q: Can I trace Focus Logística tool calls in my OpenAI Agents SDK dashboard?

Yes. Every call to emitmdfe or closemdfe shows up in your OpenAI run logs. You can inspect the exact payload sent to the Focus NFe API and see how the agent resolved tax validation issues.

Run safe, production-grade transport document workflows with Focus Logística tools inside your OpenAI Agents SDK pipeline.

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 OpenAI Agents SDK

Create your Vinkius account to connect Focus Logística to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe CT-e emission via OpenAI Agents SDK

Your agent runs `emit_cte` to draft and issue Brazilian transport documents automatically. By connecting this MCP Server to your OpenAI Agents SDK setup, the agent checks tax details, fills out the recipient's CNPJ, and files the document with SEFAZ — and don't skip this — the built-in guardrails prevent the agent from submitting duplicate tax forms if a network hiccup occurs. If the government rejects the submission, the agent handles the error instead of crashing. It can run `consult_cte` to verify the state database or immediately route the issue to a human supervisor. You get clean, automated freight documentation with a clear audit trail on your OpenAI dashboard.

Automatic MDF-e closure during agent handoffs

Your delivery agent executes `close_mdfe` to shut down the transit manifest when cargo arrives at the warehouse. This MCP Server lets your OpenAI Agents SDK pass the manifest ID to a specialized logistics agent that handles the closure. It ensures your fleet never gets flagged for running overlapping routes — simple as that. This handoff happens behind the scenes. The primary agent coordinates the overall delivery run, then hands off the technical API call to a sub-agent armed with `consult_mdfe` to double-check the status. You avoid complex state-machine code in Python because the SDK handles the agent-to-agent negotiation.

Instant XML extraction for compliance archives

Your agent uses `download_xml` to grab official SEFAZ-signed files directly for compliance audits. Your OpenAI Agents SDK pipeline can retrieve these files the second a transport document is approved. The agent then saves the file directly to your secure cloud storage. If a driver gets stopped at a state border, your support agent can run `consult_cte` to pull the active status and dispatch the XML instantly. This protects your operations from costly delays and keeps your transport documents perfectly synchronized with government servers.

Setup guide

Set up Focus Logística MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Focus Logística tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Focus Logística tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Focus Logística tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Focus Logística Agent",
            instructions="You have access to Focus Logística tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

If SEFAZ times out during `emit_cte`, configure your OpenAI Agents SDK agent to run `consult_cte` before attempting a retry. This prevents duplicate document submissions and keeps your tax records clean.

Yes. Every call to `emit_mdfe` or `close_mdfe` shows up in your OpenAI run logs. You can inspect the exact payload sent to the Focus NFe API and see how the agent resolved tax validation issues.

The SDK allows you to define pre-execution checks. This ensures your agent cannot trigger `cancel_cte` on a document that is already closed or older than the legal cancellation window.

Yes. You can spin up multiple specialized agents in your Python environment to run `emit_cte` and `emit_mdfe` concurrently, handling bulk shipments during peak hours.

All communication goes through Vinkius's secure sandbox directly to the Focus NFe API. Your sensitive Brazilian tax registry numbers (CNPJ), cargo values, and transport keys are never cached or exposed to the LLM provider.

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