How to Use the NFe.io MCP in LangChain

Q: How do I connect NFe.io to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize an MCP client via MultiServerMCPClient pointing to your endpoint URL. Call client.gettools() and pass the array to your ReAct agent.

Q: Can LangChain agents read past NFe.io invoices?

Yes. The agent calls getserviceinvoice or getmerchandiseinvoice with the document ID. It reads the returned JSON and answers questions about specific line items or tax totals.

Build multi-step billing pipelines and ReAct agents that issue Brazilian tax invoices directly through LangChain.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Invoice Creation in LangChain

The `issue_service_invoice` and `issue_merchandise_invoice` tools let your MCP agent generate Brazilian tax documents straight from a prompt. You pipe customer data from your CRM directly into the tool call. The agent formats the payload, submits it, and waits for the API response. Because this runs inside a chain, you pass the output to the next step automatically. If an invoice fails due to a bad city code, the agent catches the error and retries. You see the exact token usage and latency for every API call inside LangSmith.

Manage Company Tax Profiles

Use the `create_company` and `list_companies` tools to onboard new issuers into your billing system. Your agent reads a local JSON file of new clients and maps their tax IDs to the API payload. It registers them instantly. Need specific details for an audit? The `get_company_details` tool pulls down the exact configuration for any registered issuer. You pipe that data straight into a reporting script or vector store without writing custom wrappers.

Handle Billing Reversals

The `cancel_service_invoice` and `cancel_merchandise_invoice` tools give your agent the ability to void tax documents. When a customer requests a refund, your agent triggers the cancellation payload. It requires the original invoice ID and a justification string. You configure an MCP Server to handle the transport layer while your agent manages the logic. If the cancellation succeeds, the agent updates your database. Everything happens inside one continuous reasoning loop.

Setup guide

Set up NFe.io 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 NFe.io 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({
    "nfeio-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 NFe.io 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 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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize an MCP client via `MultiServerMCPClient` pointing to your endpoint URL. Call `client.get_tools()` and pass the array to your ReAct agent.

Yes. The agent calls `get_service_invoice` or `get_merchandise_invoice` with the document ID. It reads the returned JSON and answers questions about specific line items or tax totals.

Monitor the execution in LangSmith. Every call to the MCP tools shows the exact inputs sent to the Brazilian tax gateway and the raw errors returned.

The MCP connection defaults to stateless behavior. You need to use `client.session()` if you want the agent to remember company IDs across multiple turns.

This server processes highly sensitive Brazilian tax IDs (CNPJ/CPF) and municipal codes. The connection runs through an isolated V8 sandbox that destroys the environment after execution. No invoice data persists on the middleware layer.

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