How do I get Omie API credentials (App Key and App Secret)?

Log in to your Omie ERP account, go to **Configurações > Aplicativos** (Settings > Applications), and create a new application. Omie will automatically generate an **App Key** and **App Secret** for you. Copy both values immediately — the App Secret is shown only once. Paste them into the respective fields below. These credentials are used to authenticate all API requests.

Can I create new clients and products through this integration?

Yes! Use the `create_client` tool to add new clients (customers/suppliers) and `create_product` to add new products to your Omie catalog. You'll need to provide the data as JSON objects matching Omie's schema. The AI agent can help you structure the data correctly. After creation, you'll receive the new client or product code for future reference.

How can I monitor overdue invoices and payments?

Use `list_accounts_receivable` to see all money owed to your company, and `list_accounts_payable` to see all money you owe. Each entry includes the due date, amount, and status. You can filter and identify overdue items by comparing the due date with today's date. The AI agent can help you analyze the results and highlight which invoices need immediate attention.

What ERP modules are accessible through this API?

This integration covers the core Omie modules: **Clients** (customers, suppliers, transporters), **Products & Services** (catalog management), **Sales Orders** (pedidos de venda), **Accounts Receivable** (contas a receber), **Accounts Payable** (contas a pagar), **Bank Accounts** (contas correntes), and **Inventory/Stock** (estoque). Additional modules like NF-e, NFS-e, CRM, and purchases are available through Omie's full API but may be added in future updates.

Omie ERP MCP Server for Pydantic AI 16 tools — connect in under 2 minutes

Name: Omie ERP
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 16 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Omie ERP through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Omie ERP "
            "(16 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Omie ERP?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Omie ERP MCP Server

Connect your Omie ERP account to any AI agent and take full control of your business management workflows through natural conversation.

Pydantic AI validates every Omie ERP tool response against typed schemas, catching data inconsistencies at build time. Connect 16 tools through 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

Client Management — List, create, update, and inspect clients (customers, suppliers) with full contact and tax information
Product Catalog — Browse products and services, check details, create new items, and monitor stock levels
Sales Orders — List, create, and inspect sales orders with line items, pricing, and payment terms
Financial Monitoring — Track accounts receivable and payable to monitor cash flow and identify overdue items
Bank Accounts — List configured bank accounts and check balances for financial reconciliations
Inventory Control — Monitor stock levels, check product availability, and identify items needing reorder
Services Catalog — List and manage non-physical services offered to clients

The Omie ERP MCP Server exposes 16 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 Omie ERP to Pydantic AI via MCP

Follow these steps to integrate the Omie ERP 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 16 tools from Omie ERP with type-safe schemas

Why Use Pydantic AI with the Omie ERP MCP Server

Pydantic AI provides unique advantages when paired with Omie ERP 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 Omie ERP integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Omie ERP connection logic from agent behavior for testable, maintainable code

Omie ERP + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Omie ERP MCP Server delivers measurable value.

Type-safe data pipelines: query Omie ERP with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Omie ERP tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Omie ERP and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Omie ERP responses and write comprehensive agent tests

Omie ERP MCP Tools for Pydantic AI (16)

These 16 tools become available when you connect Omie ERP to Pydantic AI via MCP:

create_client

You must provide at minimum the business name (razao_social) and CNPJ/CPF. Optional fields include trade name, address, contacts, email, phone, payment terms, and credit limits. The response includes the newly created client code which can be used for future references. Data must be provided as a JSON object matching Omie's client schema. Create a new client (customer/supplier) in Omie ERP

create_product

You must provide at minimum the product code (codigo_produto) and description. Optional fields include NCM, unit, cost price, sale price, stock quantity, and tax configuration. The response includes the newly created product details. Data must be provided as a JSON object matching Omie's product schema. Create a new product in Omie ERP

create_sales_order

You must provide the client code (codigo_cliente) and at least one line item with product code, quantity, and price. Optional fields include discounts, taxes, shipping info, and payment terms. The response includes the newly created order code. Data must be provided as JSON matching Omie's order schema. Create a new sales order (pedido de venda) in Omie ERP

get_client

Use the client_id (codigo_cliente) obtained from list_clients to inspect full client details. This is useful for verifying client data before creating orders or invoices. Get detailed information about a specific client

get_product

Use the product_code (codigo_produto) obtained from list_products to inspect full product details. This is useful for verifying product data before creating orders. Get detailed information about a specific product

get_sales_order

Use the order_id (codigo_pedido) obtained from list_sales_orders to inspect full order details. This is useful for verifying order data before invoicing. Get detailed information about a specific sales order

get_stock_summary

Use the product_code (codigo_produto) obtained from list_products to inspect stock details. This helps determine if a product is available for sale or needs reordering. Get stock summary for a specific product

list_accounts_payable

Each entry includes supplier, due date, amount, status (open, paid, overdue), and payment method. You can optionally specify page number and records per page. Use this to monitor outgoing payments and identify bills that are due or overdue. List all accounts payable (contas a pagar) in Omie ERP

list_accounts_receivable

Each entry includes client, due date, amount, status (open, paid, overdue), and payment method. You can optionally specify page number and records per page. Use this to monitor incoming payments and identify overdue invoices that need follow-up. List all accounts receivable (contas a receber) in Omie ERP

list_bank_accounts

Each account includes bank name, agency, account number, and current balance. Use this to verify which bank accounts are available for financial transactions and reconciliations. List all bank accounts (contas correntes) configured in Omie ERP

list_clients

Each client includes business name (razao_social), trade name (nome_fantasia), CNPJ/CPF, contact information, address, and client code. You can optionally specify page number and records per page (default: 50). Use this to browse your client database or find a specific client by name or document. List all clients (customers, suppliers) in Omie ERP

list_products

You can optionally specify page number and records per page (default: 50). Use this to browse your product catalog or find a specific product by code or description. List all products and services in Omie ERP

list_sales_orders

You can optionally specify page number and records per page. Use this to browse your sales pipeline or find a specific order by number or client. List all sales orders (pedidos de venda) in Omie ERP

list_services

Services are non-physical offerings sold to clients (consulting, maintenance, etc.). You can optionally specify page number and records per page. Use this to browse your service catalog. List all services (serviços) registered in Omie ERP

list_stock

Each entry includes product code, description, quantity in stock, minimum stock level, and warehouse location. You can optionally specify page number and records per page. Use this to monitor inventory levels and identify products that need reordering. List stock/inventory levels for all products in Omie ERP

update_client

You must provide the client_id (codigo_cliente) and the fields to update. Only the fields provided in client_data will be updated. This is useful for correcting client information, updating addresses, or changing payment terms. The client_id must exist in the system. Update an existing client in Omie ERP

Example Prompts for Omie ERP in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Omie ERP immediately.

"List all my clients and show me their total outstanding balances."

"Create a new sales order for client TechCorp with 5 units of product 'Consulting Hours' at R$ 150/hour."

"Show me all overdue accounts payable and the total amount owed."

Troubleshooting Omie ERP MCP Server with Pydantic AI

Common issues when connecting Omie ERP to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Omie ERP + Pydantic AI FAQ

Common questions about integrating Omie ERP MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an 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?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Omie ERP MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.