How to Use the Focus NFe MCP in Pydantic AI

Validate your Brazilian tax payloads at runtime using Pydantic AI and Focus NFe.

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 Pydantic AI

Create your Vinkius account to connect Focus NFe to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe invoice emission with Pydantic AI

The `emit_nfe` and `emit_nfse` tools prevent tax errors before they reach SEFAZ by forcing strict runtime validation. When your agent uses these tools, the incoming and outgoing payloads are validated against Python models, ensuring no malformed tax data is transmitted. If the tax API returns unexpected fields, the framework raises a validation error immediately. This loud failure prevents silent data corruption, allowing your system to halt and log the issue before it affects your accounting ledgers.

Verify and query tax document states safely

The `consult_document` tool retrieves the exact status of any invoice. We parse the returned JSON structure directly into structured Python objects, giving your agent clean, typed data to make logical decisions. This structural safety is critical when routing shipments. Your agent can confidently read the approval status and trigger the physical dispatch of goods only when the invoice is confirmed as authorized.

Process XML downloads and cancellations securely

The `download_xml` tool retrieves authorized XML files to handle them as typed strings or byte streams. Your agent can parse the XML metadata to confirm the digital signature before storing it in your local archive. For cancellations, `cancel_document` ensures the cancellation event is recorded with strict type validation. Your system maintains a clean, validated audit trail of every voided transaction without relying on loose, unvalidated JSON dicts.

Setup guide

Set up Focus NFe MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "focus-nfe-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Focus NFe tools.",
)

result = await agent.run("List recent Focus NFe transactions")
print(result.output)

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 Pydantic AI

Initialize the MCP Server toolset with your Vinkius HTTP endpoint and pass it to your Agent constructor. The framework automatically maps tools like `emit_nfe` and `consult_document` to python-friendly validated functions.

Yes, by forcing the agent to conform to strict type schemas for `emit_nfse` and `emit_nfe`. The agent cannot pass arbitrary, unvalidated data structures, drastically reducing the risk of API-level validation errors.

The framework supports both Streamable HTTP and SSE transports. You run the MCP Server externally on Vinkius and connect your agent securely using the provided endpoint URL.

Yes, Pydantic AI is model-agnostic. You can connect your local models to this MCP Server to process `consult_document` or `download_xml` calls, keeping your LLM costs low while maintaining strict schema validation.

We execute all operations in an isolated V8 sandbox. Your tax credentials, municipal API keys, and XML payloads are processed entirely in memory and wiped immediately after the tool execution finishes.

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