How to Use the NFe.io MCP in LlamaIndex

Q: How do I use NFe.io tools in LlamaIndex?

Install llama-index-tools-mcp. Setup an MCP client using BasicMCPClient with your endpoint URL, then wrap it in McpToolSpec. Call await mcptoolspec.totoollistasync() and pass the list to your FunctionAgent.

Q: Can LlamaIndex issue new NFe.io invoices?

Yes. The agent calls issueserviceinvoice or issuemerchandiseinvoice to generate new documents. It then indexes the returned success payload for future semantic search.

Q: How do I filter which NFe.io tools the LlamaIndex agent sees?

Use the allowedtools parameter when creating your tool list. You restrict the agent to read-only operations by only passing the retrieval tools.

Index Brazilian tax documents and query NFe.io API data directly using LlamaIndex and RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NFe.io MCP to LlamaIndex

Create your Vinkius account to connect NFe.io 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 NFe.io with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Invoice Metadata in LlamaIndex

The `get_service_invoice` and `get_merchandise_invoice` tools pull raw billing data from the API. Your LlamaIndex application fetches the JSON response and converts it into document nodes. You embed these nodes into your vector store. This means you stop guessing what a specific invoice contains. You query your knowledge base, and the agent retrieves the exact tax breakdown or cancellation status. The data grounds the model's response in reality.

Build Searchable Company Registries

Use `list_companies` and `get_company_details` to build a local index of every issuer in your account. The agent pulls the complete list of CNPJs, municipal registrations, and address data. It pushes everything into a queryable semantic index. When a user asks which companies operate in a specific city, the agent searches the vector store. You connect to an MCP Server to keep this registry synced. The index updates whenever you run the ingestion pipeline.

Audit Webhook Configurations

The `list_webhooks` tool returns every active endpoint listening for invoice status changes. Your agent calls this tool to verify where the API sends its webhooks. It reads the URLs and event triggers. You use this MCP integration to diagnose missing notifications. The agent checks the live configuration against your internal documentation. If a webhook is missing, the agent flags the discrepancy immediately.

Setup guide

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

Install `llama-index-tools-mcp`. Setup an MCP client using `BasicMCPClient` with your endpoint URL, then wrap it in `McpToolSpec`. Call `await mcp_tool_spec.to_tool_list_async()` and pass the list to your `FunctionAgent`.

Yes. The agent calls `issue_service_invoice` or `issue_merchandise_invoice` to generate new documents. It then indexes the returned success payload for future semantic search.

Use the `allowed_tools` parameter when creating your tool list. You restrict the agent to read-only operations by only passing the retrieval tools.

No. The MCP standard handles the schema conversion automatically. The tools return structured strings. Your agent parses these into document nodes without extra boilerplate.

The server touches sensitive municipal tax codes and corporate addresses. Vinkius handles authentication upstream, requiring only a single endpoint token from your client. The MCP connection drops immediately after the data transfers to your index.

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