How to Use the Focus NFe MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system handle municipal tax variations via Focus NFe?

Yes, your agent uses emitnfse to target specific municipal prefeituras. Since municipal schemas vary across Brazil, the agent reads the documentation via the MCP Server to format the payload correctly for each city.

Q: What happens if a SEFAZ server goes down during a Focus NFe call in OpenAI Agents SDK?

The agent receives a clear error response from emitnfe or emitnfse. You can program your agent to retry the emission later or route the document through a contingency queue.

Ship production-ready Brazilian tax workflows with OpenAI Agents SDK and Focus NFe.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Focus NFe MCP to OpenAI Agents SDK

Create your Vinkius account to connect Focus NFe 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 NFe with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate NF-e and NFS-e emission with OpenAI Agents SDK

The `emit_nfe` and `emit_nfse` tools allow your Python agents to handle complex Brazilian tax compliance directly. By exposing these tools to your agent, you can issue product and service invoices programmatically without writing custom API wrappers. Your agent handles the payload structure, maps municipal tax codes, and triggers the emission in real-time. If a tax authority rejects a payload, the agent catches the error immediately. It can correct minor formatting issues or missing fields and retry the call. You get clean invoices sent to SEFAZ without manual engineering intervention.

Verify document status and fetch XML payloads

The `consult_document` tool lets your agent monitor the lifecycle of every invoice. This tool checks the state of any document, letting your workflow pause until SEFAZ authorizes the transaction. Once authorized, your agent calls `download_xml` to retrieve the final XML file. This file can be saved directly to your database or forwarded to the customer's accountant. You get a reliable way to keep your internal ERP system in sync with the tax authorities.

Handle invoice cancellations with built-in safety

The `cancel_document` tool lets your agent void an issued invoice when a transaction falls through. You provide the justification, and the agent communicates directly with the municipal or state server to process the cancellation within the legal timeframe. Using this MCP Server within the OpenAI framework ensures your agent only triggers cancellations under strict conditions. Guardrails validate the agent's decision before executing the tool, preventing accidental tax voids that could disrupt your accounting.

Setup guide

Set up Focus NFe 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 NFe tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Focus NFe 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 NFe 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 NFe Agent",
            instructions="You have access to Focus NFe 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 NFe 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 NFe MCP in OpenAI Agents SDK

Install the SDK using pip, then initialize the server connection using MCPServerStreamableHttp. Pass the MCP Server endpoint to your Agent constructor. The agent will auto-discover tools like `emit_nfe` and `consult_document` with zero extra configuration.

Yes, your agent uses `emit_nfse` to target specific municipal prefeituras. Since municipal schemas vary across Brazil, the agent reads the documentation via the MCP Server to format the payload correctly for each city.

The agent receives a clear error response from `emit_nfe` or `emit_nfse`. You can program your agent to retry the emission later or route the document through a contingency queue.

No, the Vinkius platform handles authentication at the transport layer. Your Python agent needs a single Vinkius endpoint token to securely access all five tools, including `download_xml` and `cancel_document`.

We route all XML payloads and invoice metadata through a secure, ephemeral V8 isolate sandbox. We don't store your tax data, corporate CNPJs, or financial figures on Vinkius servers after the tool execution completes.

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