How to Use the Conta Azul MCP in Pydantic AI

Q: How does Pydantic AI validate data from the Conta Azul MCP server?

The framework maps the JSON schemas exposed by tools like getproduct to Pydantic models at runtime. If the ERP returns a product unit that doesn't match your schema, the tool execution halts immediately with a validation error.

Q: Can I use Pydantic AI to automate Brazilian tax compliance?

Yes, you can write agents that query listnfe and match the invoice metadata against your internal databases. The strict validation guarantees that your compliance scripts only process correctly formatted government invoices.

Build type-safe Python agents that validate Conta Azul ERP data at runtime using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conta Azul MCP to Pydantic AI

Create your Vinkius account to connect Conta Azul 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 Conta Azul with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Customer Management via Pydantic AI

The `get_customer` tool retrieves static financial profiles via UUID, allowing Pydantic AI to validate Brazilian tax IDs at runtime. If the ERP returns a malformed CPF or CNPJ, the framework raises a validation error immediately. When creating new profiles, the agent runs `create_customer` using strict type definitions. This prevents corrupt contact info from entering your Brazilian ERP database, keeping your pipeline clean.

Validate Invoices and Sales Records

The `get_sale` tool exposes exact accounting matrices that Pydantic AI parses into strongly typed Python objects. This MCP integration ensures your agent never processes a sale with missing tax fields or incorrect currency values. For bulk audits, the agent invokes `list_sales` to check pending invoices. Because every field matches a Pydantic model, your automated accounting scripts fail loudly if the ERP data structure changes.

Manage Service Pricing and DRE Classifications

The `create_service` tool registers billable services with strict pricing validation enforced by your Pydantic AI schema. This blocks your agent from creating services with negative values or incorrect currency codes. To organize your ledger, the agent runs `list_categories` to fetch the analytical plan of your DRE. The framework validates these financial categories, ensuring your automated reports map to valid accounts.

Setup guide

Set up Conta Azul 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": {
        "conta-azul-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Conta Azul 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 Conta Azul. 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 Conta Azul 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 Conta Azul MCP in Pydantic AI

The framework maps the JSON schemas exposed by tools like `get_product` to Pydantic models at runtime. If the ERP returns a product unit that doesn't match your schema, the tool execution halts immediately with a validation error.

Yes, you can write agents that query `list_nfe` and match the invoice metadata against your internal databases. The strict validation guarantees that your compliance scripts only process correctly formatted government invoices.

It connects via the MCPToolset using either Streamable HTTP or SSE transports. This establishes a secure connection to the Vinkius-hosted server, letting your agent run tools like `list_contracts` instantly.

You define custom Pydantic fields that parse the Real currency values returned by `list_products`. The agent automatically converts these values into Python Decimal types for safe financial calculations.

Every transaction processed by Pydantic AI goes through Vinkius's zero-trust sandbox. This keeps the MCP Server execution fully secure. Your contract details from `list_contracts` are processed in memory and never written to persistent logs, keeping your Brazilian corporate data safe.

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