How to Use the Focus NFe MCP in LlamaIndex

Q: Does LlamaIndex query past invoices processed by Focus NFe?

Yes. Your agent uses consultdocument to fetch the details, which you then ingest into your vector index for semantic search and retrieval.

Q: How does LlamaIndex handle municipal tax rules with Focus NFe?

The agent calls emitnfse with the required city-specific tax payload. Because the tool handles the complex municipal API mapping, your agent only needs to supply the basic service details.

Q: How do I run semantic audits on XML documents in LlamaIndex?

You use downloadxml to get the raw tax XML. The agent parses the node structure and indexes the text, allowing natural language queries over your official tax records.

Index Brazilian tax data and run live invoice actions inside your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Focus NFe MCP to LlamaIndex

Create your Vinkius account to connect Focus NFe 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 NFe with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index and query live invoice data in LlamaIndex

Use `consult_document` through this MCP Server to get detailed tax payloads and index them directly into your vector database. This lets your query engine search past transactions and answer complex financial questions using grounded, real-time fiscal data. By feeding the output of this tool into your index, you prevent model hallucinations regarding order statuses. Your agent queries the live API, updates the document store, and provides accurate billing details to your users.

Direct invoice emission from semantic search

Execute `emit_nfe` to generate official product invoices based on unstructured data fetched from your knowledge base. The agent extracts customer details and line items from a contract or support ticket, formats the tax payload, and submits it to SEFAZ. For service-based contracts, the agent relies on `emit_nfse` to register the transaction with municipal authorities. This turns your static document indexes into active systems that execute legal tax operations directly from user queries.

Get XML payloads for compliance indexing

Call `download_xml` to fetch the authorized XML string for any processed transaction. This raw fiscal data is parsed and stored in your document store, allowing your compliance agents to run semantic audits on tax fields. If a customer disputes a charge, the agent runs `cancel_document` to void the invoice. The local vector index updates immediately to reflect the cancellation, ensuring your knowledge base matches the official government registry via this MCP integration.

Setup guide

Set up Focus NFe 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 NFe 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 NFe tools.",
)
response = await agent.run("List recent Focus NFe 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 NFe 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 NFe MCP in LlamaIndex

Install the llama-index-tools-mcp package and initialize the BasicMCPClient with your Vinkius URL. Convert it to a tool specification using McpToolSpec and pass it to your FunctionAgent.

Yes. Your agent uses `consult_document` to fetch the details, which you then ingest into your vector index for semantic search and retrieval.

The agent calls `emit_nfse` with the required city-specific tax payload. Because the tool handles the complex municipal API mapping, your agent only needs to supply the basic service details.

You use `download_xml` to get the raw tax XML. The agent parses the node structure and indexes the text, allowing natural language queries over your official tax records.

Your sensitive XML payloads and tax ID numbers are processed entirely within secure, ephemeral V8 isolates. Vinkius executes the server statelessly, meaning your financial data is never written to disk or stored outside the active session.

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