How to Use the Focus Varejo MCP in AutoGen

Q: How do I connect Focus Varejo to my AutoGen agents?

Install autogen-extmcp and initialize mcpservertools with your endpoint URL. Pass the generated tool list directly to your AssistantAgent constructor.

Q: Can multiple AutoGen agents share the Focus Varejo tools?

Yes. You give consultnfce to a read-only auditing agent while restricting emitnfce to a highly privileged execution agent. They collaborate over the shared chat context.

Deploy multi-agent AutoGen systems that debate and execute Focus Varejo tax operations autonomously.

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 AutoGen

Create your Vinkius account to connect Focus Varejo 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 Focus Varejo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Tax Compliance via MCP Server

Issuing retail invoices requires strict validation before hitting the SEFAZ servers. You build an AutoGen setup via this MCP server where a Validator Agent drafts the XML payload and a Compliance Agent reviews it. They negotiate the exact tax rates and product codes before anyone touches the `emit_nfce` tool. If the SEFAZ API rejects the emission, the agents don't just throw an error. They read the rejection code, discuss the missing parameters, and attempt a correction. The entire process happens autonomously, keeping your point-of-sale systems online without manual intervention.

Autonomous Manifest Approvals

Acknowledging inbound invoices carries legal weight. You configure a Logistics Agent to monitor incoming shipments and an Accounting Agent to verify the purchase orders. They debate whether to confirm the operation using `manifest_nfe`. If the purchase order doesn't match the invoice value, the Accounting Agent blocks the manifest action. It instructs the Logistics Agent to run `list_received_nfse` to find the discrepancy. Your team only steps in when the agents fail to reach a consensus.

Telecom Billing and Cancellation

Telecom billing requires issuing thousands of NFCom documents via this MCP integration. A Billing Agent handles the batch processing by calling `emit_nfcom` for each customer. Meanwhile, an Audit Agent monitors the success rate in real time. When a customer cancels their plan mid-cycle, the Audit Agent immediately triggers `consult_nfcom` to check the document status. If the invoice hasn't been paid, it instructs the Billing Agent to execute `cancel_nfce` to void the charge. They coordinate the exact sequence to prevent double billing.

Setup guide

Set up Focus Varejo 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 Focus Varejo 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="Focus Varejo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Focus Varejo 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="Focus Varejo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Focus Varejo 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 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 AutoGen

Install `autogen-ext[mcp]` and initialize `mcp_server_tools` with your endpoint URL. Pass the generated tool list directly to your `AssistantAgent` constructor.

Yes. You give `consult_nfce` to a read-only auditing agent while restricting `emit_nfce` to a highly privileged execution agent. They collaborate over the shared chat context.

The agents notice the failure and discuss the next steps. They might decide to wait five seconds before retrying the exact same `consult_nfcom` call, entirely driven by their system prompts.

The MCP schema provides the exact parameter definitions. The agents read these definitions and format the JSON or XML payloads correctly before making the API request.

You never pass Focus API keys through your local environment. Vinkius handles the underlying auth, so your agents only send the raw customer names and tax codes to our ephemeral sandbox. We process the request and immediately drop the connection state.

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