Conta Azul MCP Server for Pydantic AI 15 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Conta Azul through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Conta Azul "
"(15 tools)."
),
)
result = await agent.run(
"What tools are available in Conta Azul?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Conta Azul MCP Server
Connect your Conta Azul account to any AI agent and take full control of your Brazilian business ERP and financial management through natural conversation.
Pydantic AI validates every Conta Azul tool response against typed schemas, catching data inconsistencies at build time. Connect 15 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Customer Management — List and search for customers (PJ/PF), audit fiscal documents (CNPJ/CPF), and create new financial entities natively
- Inventory & Services — Map physical products (SKU) and intangible services, retrieve pricing, units of measure, and create new billable components
- Sales Monitoring — List continuous logs of confirmed sales, retrieve detailed accounting matrices for units, and verify invoice statuses
- Recurrence Tracking — Audit financial contracts and automatic agreements to monitor monthly/annual technical debt and expiration dates
- Fiscal Compliance (NF-e) — Retrieve governmental emissions records (NF-e) and validate SEFAZ approval statuses for product invoices
- Financial Structure — Access hierarchical category trees (DRE) and map bank accounts to reconcile monetary positions and internal cash flow
The Conta Azul MCP Server exposes 15 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Conta Azul to Pydantic AI via MCP
Follow these steps to integrate the Conta Azul MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 15 tools from Conta Azul with type-safe schemas
Why Use Pydantic AI with the Conta Azul MCP Server
Pydantic AI provides unique advantages when paired with Conta Azul through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Conta Azul integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Conta Azul connection logic from agent behavior for testable, maintainable code
Conta Azul + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Conta Azul MCP Server delivers measurable value.
Type-safe data pipelines: query Conta Azul with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Conta Azul tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Conta Azul and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Conta Azul responses and write comprehensive agent tests
Conta Azul MCP Tools for Pydantic AI (15)
These 15 tools become available when you connect Conta Azul to Pydantic AI via MCP:
create_customer
Injetar novo registro financeiro PF/PJ definindo estrutura formal dentro do ERP
create_product
Mapear bens tangíveis definindo novos componentes faturáveis em Real financeiro
create_service
Inserir prestação ativa intangível estritamente precificada na contabilidade
get_customer
Extrair perfil estático financeiro via UUID rastreando limites PF/PJ explícitos
get_product
Ler dados de um item físico individual incluindo limite e unidade de medida
get_sale
Visualizar blocos confirmados incluindo matrizes exatas contábeis da venda UUID
list_bank_accounts
Mapear bancos físicos conciliando integração extraindo posições monetárias
list_categories
g. Despesas, Receitas) que formam a espinha dorsal de DRE validada base ContaAzul. Determinar limites contábeis de Plano Analítico nativo classificando recursos
list_contracts
Pesquisar recorrências atestando acordos automáticos limitando vencimentos
list_customers
Listar base de clientes paginada extraindo entidades corporativas no ERP
list_nfe
Buscar listagem governamental acoplada de emissões NF (Notas de Produto)
list_products
Mapear itens físicos catalogados incluindo valores de SKU extraídos estaticamente
list_sales
Listar logs contínuos extraídos avaliando faturas pendentes emitidas no fluxo
list_services
Ler prestação categorizada cobrável na estrutura contábil faturada paginada
search_customers
Pesquisar perfis corporativos/fiscais comparando documentos restritos via CPF/CNPJ
Example Prompts for Conta Azul in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Conta Azul immediately.
"Search for customer with CNPJ '12.345.678/0001-90'"
"List the last 5 sales"
"Check the status of my NF-e emissions for this month"
Troubleshooting Conta Azul MCP Server with Pydantic AI
Common issues when connecting Conta Azul to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiConta Azul + Pydantic AI FAQ
Common questions about integrating Conta Azul MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect Conta Azul with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Conta Azul to Pydantic AI
Get your token, paste the configuration, and start using 15 tools in under 2 minutes. No API key management needed.