How to Use the Focus Admin MCP in LlamaIndex

Q: How do I register the Focus Admin tools in LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient. Wrap it in a McpToolSpec and call totoollistasync() to pass the tools to your LlamaIndex FunctionAgent.

Q: Can LlamaIndex query past invoice data retrieved via Focus Admin?

Yes, you can query older documents by fetching them with listnfebyperiod and indexing them into a vector store. The LlamaIndex agent will retrieve the exact invoice context to ground its answers.

Q: How does the Focus Admin MCP server handle PDF storage in LlamaIndex?

The downloadnfedanfe tool returns the DANFE as a base64 string. You must write a simple Python function to convert this string back into a PDF file before LlamaIndex can parse it.

Q: Can I filter which Focus NFe tools my LlamaIndex agent can access?

Yes, you can use the allowedtools list in LlamaIndex to restrict access. For instance, you can expose only listnfebyperiod while blocking destructive tools like inutilizenumbering.

Index your Brazilian fiscal documents directly into vector stores using LlamaIndex and the Focus Admin MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Focus Admin MCP to LlamaIndex

Create your Vinkius account to connect Focus Admin 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 Admin with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index raw XML data for semantic search

The `download_nfe_xml` tool downloads the official XML structure of any invoice directly from the Focus NFe API. Your LlamaIndex pipeline can ingest this raw text, chunk it, and store it in a vector database for semantic querying. You can also use `download_event_xml` to retrieve specific event histories, like corrections or cancellations. That's how you ask your agent conversational questions about invoice histories instead of manually searching database tables.

Query incoming DF-e documents using this MCP Server

The `distribute_dfe` tool queries the national database via NSU to locate documents issued against your company's CNPJ. It pulls these records directly into your LlamaIndex knowledge base for instant indexing. Your agent can then search these distributed documents to identify unrecognized invoices. This setup helps prevent tax fraud by matching incoming fiscal documents against your actual purchase orders.

Build service invoice knowledge bases

The `list_nfse_received` tool pulls all municipal service invoices received by your organization. LlamaIndex indexes these documents, making it simple to run queries across vendor names, service descriptions, and tax rates. Combine this with `list_nfse_emitted` to build a complete repository of your outbound service transactions. The agent searches these indexes to answer complex audit questions without querying SQL databases directly.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient`. Wrap it in a `McpToolSpec` and call `to_tool_list_async()` to pass the tools to your LlamaIndex `FunctionAgent`.

Yes, you can query older documents by fetching them with `list_nfe_by_period` and indexing them into a vector store. The LlamaIndex agent will retrieve the exact invoice context to ground its answers.

The `download_nfe_danfe` tool returns the DANFE as a base64 string. You must write a simple Python function to convert this string back into a PDF file before LlamaIndex can parse it.

Yes, you can use the `allowed_tools` list in LlamaIndex to restrict access. For instance, you can expose only `list_nfe_by_period` while blocking destructive tools like `inutilize_numbering`.

All XML structures, tax values, and corporate identifiers are processed in memory within isolated, zero-trust environments. Vinkius never caches your Focus NFe API credentials or the fiscal payloads retrieved by the tools.

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