How to Use the Focus Varejo MCP in Mastra AI

Q: How can I make my Focus Varejo integration with Mastra AI more reliable?

Use Mastra AI's built-in workflow engine. Wrap your emitnfce or manifestnfe calls in a step with automatic retries. This handles temporary network issues or API downtime without crashing your process.

Q: Can Mastra AI handle a failed invoice from Focus Varejo?

Yes. Create a workflow where one step calls emitnfce. Add a conditional branch that checks the tool's output. If it indicates failure, trigger a second step that alerts an administrator or attempts a corrective action, like using cancelnfce.

Q: What's a good workflow for processing inbound documents with Focus Varejo and Mastra AI?

Set up a recurring Mastra AI job. The first step calls listreceivednfse to get new invoices. Then, loop through the results and pass each one to another step that calls manifestnfe to formally acknowledge receipt.

Q: How does this MCP server connect to Mastra AI?

You add the Vinkius server URL to your MCPClient configuration in Mastra. Your agent can then see and use all 8 Focus Varejo tools, like emitnfce and consultnfcom, as if they were native functions.

Build resilient fiscal automation for your backend with Mastra AI and the Focus Varejo toolset.

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 Mastra AI

Create your Vinkius account to connect Focus Varejo to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Unattended Invoice & Manifest Workflows

The Focus Varejo tools let you automate Brazilian tax documents. Mastra AI makes that automation reliable. You can build a workflow that calls `emit_nfce` for a new sale. If the API call fails, Mastra's engine can automatically retry it with exponential backoff. This is critical for services that can have intermittent downtime. Instead of your code breaking, the workflow waits and retries, ensuring the invoice is eventually issued by this MCP Server. You can apply the same logic to `manifest_nfe` or `emit_nfcom` for dependable processing.

Smart Workflows for Complex Rules

Fiscal rules aren't always straightforward. With Mastra AI, you can build conditional logic around the Focus Varejo tools. For example: after calling `emit_nfce`, use `consult_nfce` to check its status. If the status is 'rejected,' trigger a different branch of your workflow that notifies a human for manual review. This lets you build robust systems that handle edge cases gracefully. You can create a flow that tries to issue an invoice, checks the result, and if necessary, attempts to `cancel_nfce` before escalating the problem. This MCP server gives you the verbs; Mastra gives you the grammar.

Automate NFCom and NFS-e with Mastra AI

This isn't just for retail. The server includes `emit_nfcom` and `consult_nfcom` for handling telecommunication service invoices. You can build a Mastra AI workflow that automates your monthly billing run, issuing an NFCom for every active subscription. The `list_received_nfse` tool is also included. Set up a daily workflow that fetches all new service invoices your company has received, then passes them to another system for payment processing. It’s set-and-forget automation for your accounts payable.

Setup guide

Set up Focus Varejo MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Focus Varejo tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "focus-varejo-mcp-client",
  servers: {
    "focus-varejo-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Focus Varejo Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Focus Varejo tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Focus Varejo transactions"
);
console.log(result.text);

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 Mastra AI

Use Mastra AI's built-in workflow engine. Wrap your `emit_nfce` or `manifest_nfe` calls in a step with automatic retries. This handles temporary network issues or API downtime without crashing your process.

Yes. Create a workflow where one step calls `emit_nfce`. Add a conditional branch that checks the tool's output. If it indicates failure, trigger a second step that alerts an administrator or attempts a corrective action, like using `cancel_nfce`.

Set up a recurring Mastra AI job. The first step calls `list_received_nfse` to get new invoices. Then, loop through the results and pass each one to another step that calls `manifest_nfe` to formally acknowledge receipt.

You add the Vinkius server URL to your `MCPClient` configuration in Mastra. Your agent can then see and use all 8 Focus Varejo tools, like `emit_nfce` and `consult_nfcom`, as if they were native functions.

The MCP server acts as a secure proxy. Your Mastra AI agent sends the request, the server forwards it to the Focus Varejo API, and the response is sent back. No sensitive NF-e or CT-e manifest data is logged or stored on the Vinkius MCP 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