How to Use the NFe.io MCP in AutoGen

Q: How do I load NFe.io tools into AutoGen?

Install autogen-extmcp. Load the MCP tools by calling mcpservertools with a StreamableHttpServerParams object. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Does the framework handle schema conversion automatically?

Yes. The McpToolAdapter translates the server definitions into native function calls. You never write manual wrappers for the API endpoints.

Give your AutoGen agents the ability to debate, validate, and issue Brazilian tax invoices autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NFe.io MCP to AutoGen

Create your Vinkius account to connect NFe.io 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 NFe.io with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Issue Invoices via MCP Server

The `issue_service_invoice` and `issue_merchandise_invoice` tools allow your agents to generate tax documents after reaching a consensus. A data-entry agent drafts the payload while a compliance agent checks the city codes. They debate the structure until the payload is perfect. Once they agree, the execution agent fires the tool call. This prevents bad requests from reaching the API. You catch municipal code errors during the conversation phase, saving you from immediate invoice rejections.

Autonomous Company Onboarding

Use the `create_company` and `list_companies` tools to manage your issuer accounts. A setup agent reviews a new client's tax details. A secondary agent verifies the CNPJ format before executing the creation payload. Connecting an MCP Server gives these agents direct write access to your environment. They negotiate the exact configuration parameters required by the Brazilian tax authority. You just watch the logs as they work.

Negotiated Billing Cancellations

The `cancel_service_invoice` and `cancel_merchandise_invoice` tools let your agents void transactions safely. A customer support agent proposes a cancellation. A finance agent reviews the request and demands a valid justification string. The tools require strict inputs to work. The agents argue over the justification text until it meets your internal policies. Only then does the system actually send the cancellation request.

Setup guide

Set up NFe.io 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 NFe.io 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="NFe.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]`. Load the MCP tools by calling `mcp_server_tools` with a `StreamableHttpServerParams` object. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You assign the tools to a specific execution agent. The other agents in the chat send messages to the executor when they agree a tax document needs to be created or cancelled.

They read the schema provided by the MCP standard. If a payload fails, the API returns an error message. The agents read the error, discuss the fix, and retry the call.

Yes. The `McpToolAdapter` translates the server definitions into native function calls. You never write manual wrappers for the API endpoints.

This setup processes live merchandise values and service descriptions. The MCP Server operates inside a zero-trust sandbox that isolates the request. The environment wipes itself clean the moment the API responds.

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