How to Use the Focus Varejo MCP in LangChain

Q: How do I initialize the Focus Varejo tools in LangChain?

Install langchain-mcp-adapters and pass your endpoint URL to MultiServerMCPClient. Then call client.gettools() and inject them into your ReAct agent constructor.

Q: Can LangChain handle Focus Varejo API errors automatically?

Yes. You wrap tools like cancelnfce in a retry chain. If the SEFAZ API rejects the cancellation, your agent catches the error and executes a predefined fallback strategy.

Q: How does LangChain trace Focus Varejo payloads?

Every call to emitnfce or listreceivednfse shows up in your LangSmith dashboard. You see the exact inputs, outputs, and latency for every MCP tool invocation.

Build automated retail invoice pipelines in LangChain by connecting Focus Varejo tools directly to your reasoning agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Focus Varejo MCP to LangChain

Create your Vinkius account to connect Focus Varejo 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 Varejo with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Tax Document Workflows with this MCP Server

This MCP server exposes eight Focus Varejo tools that plug right into LangChain's ReAct agents. Your agent decides the order of operations based on real-time API responses. It triggers `emit_nfce` for a retail sale, reads the output, and immediately passes the transaction ID to your database. If a network timeout occurs, the chain doesn't just crash. You configure fallback logic where the agent automatically calls `consult_nfce` to check the invoice status. Every step gets logged in LangSmith, showing exactly how many tokens the model used to format the XML payloads.

Automate Inbound Logistics Manifests

Handling inbound freight and vendor invoices requires explicit acknowledgment. You build a chain that monitors an inbox, extracts the access keys, and feeds them into the `manifest_nfe` and `manifest_cte` tools. The output from these manifest actions becomes the input for your inventory management node. Your LangChain agent handles the entire sequence without human intervention, keeping you compliant with Brazilian tax regulations while your supply chain keeps moving.

Telecom Invoice Generation

Issuing telecom invoices involves strict regulatory formatting. You configure an agent to format the billing data and push it through the `emit_nfcom` tool. The agent waits for the synchronous success response before updating the customer's billing record. When a customer disputes a charge, you trigger a localized graph that runs `consult_nfcom` to verify the exact document status. If an error surfaces, the agent parses the SEFAZ rejection code and alerts your accounting team via a separate Slack integration.

Setup guide

Set up Focus Varejo 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 Varejo 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-varejo-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 Varejo 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 Varejo 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 Varejo MCP in LangChain

Install `langchain-mcp-adapters` and pass your endpoint URL to `MultiServerMCPClient`. Then call `client.get_tools()` and inject them into your ReAct agent constructor.

Yes. You wrap tools like `cancel_nfce` in a retry chain. If the SEFAZ API rejects the cancellation, your agent catches the error and executes a predefined fallback strategy.

Every call to `emit_nfce` or `list_received_nfse` shows up in your LangSmith dashboard. You see the exact inputs, outputs, and latency for every MCP tool invocation.

You build a sequential chain. The agent pulls customer data from your SQL tool, formats it, and passes it directly to `emit_nfce` to generate the retail invoice.

Tax identification numbers and billing addresses pass strictly through our V8 Isolate Sandbox. Vinkius destroys the ephemeral container immediately after the Focus NFe API returns the invoice status. Nothing persists on our infrastructure.

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