How to Use the Focus NFe MCP in AutoGen

Q: How do AutoGen agents handle municipal service tax with Focus NFe?

Your specialized service agent calls emitnfse when the task involves non-physical goods. The agent negotiates the correct service code with your database agent before calling the tool.

Build multi-agent tax clearance workflows in AutoGen with automated invoice generation and verification.

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 AutoGen

Create your Vinkius account to connect Focus NFe 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 NFe with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven invoice emission in AutoGen

Use `emit_nfe` within an MCP-enabled multi-agent conversation to generate product invoices only after your billing and inventory agents agree on the order details. The finance agent constructs the tax payload, while the compliance agent checks the calculations before triggering the API. When dealing with services, the system routes the request to `emit_nfse` to handle municipal tax authorities. This collaborative approach ensures that no invoice is submitted to the government with incorrect tax rates or missing customer data.

Automated checks and error correction

Run `consult_document` to monitor the state authorization process through a dedicated supervisor agent. If SEFAZ returns a temporary rejection, the agent parses the error code and initiates a debate to correct the payload. Once the issue is resolved, the agent re-submits the invoice. This multi-agent feedback loop handles complex Brazilian tax errors autonomously, reducing manual engineering intervention to zero.

Compliant cancellations and XML archiving

Trigger `cancel_document` via a dedicated risk agent when a transaction is flagged for fraud or payment failure. The agent coordinates with the logistics agent to halt shipping before submitting the cancellation request to the government. Simultaneously, the archiving agent uses `download_xml` to get the final authorized XML file. This keeps your records audit-ready without manual exports, using the MCP Server's native download utility.

Setup guide

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

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

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

Use the autogen-ext package and initialize the tools using the mcp_server_tools function with your Vinkius HTTP URL. Pass the resulting tool list to your AssistantAgent constructor.

Yes. A risk agent can identify a payment failure and instruct the billing agent to call `cancel_document` to void the authorized invoice.

Your specialized service agent calls `emit_nfse` when the task involves non-physical goods. The agent negotiates the correct service code with your database agent before calling the tool.

You pass multiple server parameter configurations to your agent setup. This lets you combine Brazilian tax tools with other database or communication servers in the same agent conversation.

All communications are encrypted in transit, and the server runs inside an isolated, stateless V8 sandbox. Your corporate tax IDs and XML data are never logged or stored on the Vinkius platform, ensuring complete operational privacy.

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