How to Use the Focus NFe MCP in LangChain

Q: Does LangChain handle both product and service invoices with Focus NFe?

Yes. Your agent uses emitnfe for physical products and emitnfse for services. The model analyzes the incoming order data to select the correct tool automatically.

Q: How does LangChain handle SEFAZ timeouts using Focus NFe?

Your chain uses consultdocument to poll the status if the initial emission returns a pending state. You configure standard LangChain retry runnables to handle these network delays gracefully.

Q: How do I download raw XML files directly to my storage via LangChain?

The downloadxml tool returns the authorized XML payload directly to your agent. The chain then forwards this string to your cloud storage bucket or local database in the next step.

Run Brazilian tax document pipelines natively in LangChain by linking real-time invoice generation directly to your agent chains.

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 LangChain

Create your Vinkius account to connect Focus NFe to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated invoice emission in LangChain chains

Use `emit_nfe` via your MCP connection to instantly generate and submit Brazilian product invoices directly from your active multi-step chains. Your agent grabs order data from your database, formats the payload, and sends it to the state tax authority without manual intervention. If the transaction involves service charges instead of physical goods, the agent switches to `emit_nfse` to clear municipal tax requirements. The output is processed dynamically, allowing subsequent chain steps to handle shipping or billing immediately based on the API response.

Real-time document status checks and downloads

Run `consult_document` to check the current authorization status of any invoice before initiating shipping workflows. The agent handles the asynchronous wait times of state servers by polling the status, feeding the clean JSON response directly into your decision logic. Once authorized, the chain triggers `download_xml` to grab the raw XML payload required for fiscal compliance. This file is passed directly to your cloud storage adapters or email tools in the next chain step, keeping your records updated automatically.

Instant cancellations for failed transactions

Invoke `cancel_document` to handle returns, order modifications, or payment failures without leaving your agent loop. The agent evaluates the failure state, builds the cancellation payload, and submits it to the tax authority within the legal window. This setup avoids the overhead of building custom API integrations for tax web services. By exposing this MCP Server to your LangChain agents, you build self-healing payment and logistics loops that resolve tax errors on the fly.

Setup guide

Set up Focus NFe MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Focus NFe tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "focus-nfe-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Focus NFe transactions"
    })
    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 LangChain

You install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with the Vinkius endpoint. From there, extract the tools and pass them directly to your agent constructor to start emitting invoices.

Yes. Your agent uses `emit_nfe` for physical products and `emit_nfse` for services. The model analyzes the incoming order data to select the correct tool automatically.

Your chain uses `consult_document` to poll the status if the initial emission returns a pending state. You configure standard LangChain retry runnables to handle these network delays gracefully.

The `download_xml` tool returns the authorized XML payload directly to your agent. The chain then forwards this string to your cloud storage bucket or local database in the next step.

Vinkius hosts the server in a zero-trust, ephemeral V8 isolate sandbox that processes your invoice payloads and XML files in memory. No transaction data or tax identifiers are persisted on the host, keeping your fiscal records compliant and private.

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