How to Use the Focus Varejo MCP in LlamaIndex

Q: How do I load Focus Varejo tools into LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. Wrap it with McpToolSpec and pass the resulting tool list to your FunctionAgent.

Q: Can LlamaIndex search through Focus Varejo invoice data?

Yes. You write a script that calls listreceivednfse, converts the JSON output into LlamaIndex Document objects, and loads them into your vector store for semantic querying.

Index retail tax documents directly into your LlamaIndex knowledge base using the Focus Varejo integration.

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 LlamaIndex

Create your Vinkius account to connect Focus Varejo to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG Pipelines in LlamaIndex

Tax compliance isn't just about issuing documents; it's about querying them later. When you connect this MCP server, your LlamaIndex application pulls raw JSON responses from the Focus NFe API and converts them into searchable documents. You run `list_received_nfse` to fetch incoming service invoices and immediately embed them into your vector store. When an accountant asks about last month's software expenses, your agent doesn't guess. It runs a semantic search over the indexed API data. The system retrieves the exact service invoices, cross-references vendor names, and generates an answer grounded in hard financial records.

Index Retail and Telecom Emissions

Retailers generate thousands of NFC-e receipts daily. Using this MCP integration, you configure a scheduled LlamaIndex job that runs `consult_nfce` or `consult_nfcom` on recent transactions. The agent takes the SEFAZ authorization protocols and indexes them alongside your internal sales data. This creates a single place to search. A store manager asks why a specific transaction failed, and the agent retrieves the exact rejection reason from the embedded `emit_nfce` response. You stop digging through raw logs and start asking questions in plain English.

Track Inbound Freight Manifests

Logistics operations require constant oversight of incoming shipments. Your agent uses the `manifest_cte` and `manifest_nfe` tools to acknowledge freight documents, then indexes those confirmations. Now your knowledge base understands your supply chain state. If a warehouse supervisor queries the status of a specific truck delivery, LlamaIndex pulls the manifest confirmation directly from the vector index. The response includes the exact timestamp and access key required for auditing.

Setup guide

Set up Focus Varejo MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Focus Varejo MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Focus Varejo tools.",
)
response = await agent.run("List recent Focus Varejo data")

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 LlamaIndex

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Wrap it with `McpToolSpec` and pass the resulting tool list to your `FunctionAgent`.

Yes. You write a script that calls `list_received_nfse`, converts the JSON output into LlamaIndex `Document` objects, and loads them into your vector store for semantic querying.

It does. You restrict your LlamaIndex agent to only use read-only tools like `consult_nfce` while blocking access to execution tools like `cancel_nfce`.

Your agent handles this via iterative tool calls. It requests the first batch of invoices, indexes them, and then uses the next page token in subsequent calls until the extraction finishes.

We route your CNPJ and transaction amounts through a zero-trust execution environment. Vinkius manages the authentication state securely, and the sandbox vanishes the moment the API returns your document status.

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