How to Use the NFe.io MCP in Pydantic AI

Q: Can Pydantic AI cancel NFe.io invoices safely?

Yes, using cancelserviceinvoice or cancelmerchandiseinvoice. The tool execution is treated as a validated step within your agent's workflow.

Q: Are NFe.io tool responses type-safe in Pydantic AI?

Yes, the MCPToolset ensures that every tool output is validated. This prevents silent failures in your invoice management system.

Get type-safe tax invoice management for Pydantic AI agents with strictly validated MCP tool responses.

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 Pydantic AI

Create your Vinkius account to connect NFe.io 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 NFe.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly typed NFe.io tools for Pydantic AI

Every tool like `issue_service_invoice` returns data that is checked against Pydantic models. If the API returns unexpected fields, your agent catches the error immediately. This ensures your agent never processes corrupt or malformed tax data. You get full runtime validation for every financial operation.

Query tax records with Pydantic AI

Use `get_merchandise_invoice` to pull invoice details into your agent's memory. The response is validated to match your expected schema before the agent acts on it. This approach prevents hallucinations in invoice processing. Your agent relies on verified, structured data for every decision.

Control issuer records in Pydantic AI

Manage companies with `create_company` using validated inputs. Your agent confirms that every registration matches your defined requirements. `list_companies` gives your agent a list of issuers that is guaranteed to match your schema. It provides a reliable foundation for your invoicing logic.

Setup guide

Set up NFe.io 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": {
        "nfeio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NFe.io 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 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 Pydantic AI

The server response is parsed against your Pydantic models at runtime. If the NFe.io data doesn't fit your schema, the agent throws a validation error.

Yes, using `cancel_service_invoice` or `cancel_merchandise_invoice`. The tool execution is treated as a validated step within your agent's workflow.

Yes, the `MCPToolset` ensures that every tool output is validated. This prevents silent failures in your invoice management system.

Provide the Vinkius-managed endpoint token to the server. The connection is encrypted and isolated from your other agent processes.

The server processes invoice metadata in an ephemeral sandbox. No data persists outside of the requested transaction, maintaining your document privacy.

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