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 LangChain 16 tools — connect in under 2 minutes

Name: Omie ERP
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 16 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Omie ERP through the Vinkius and LangChain agents can call every tool natively — combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

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 langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "omie-erp": {
            "transport": "streamable_http",
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
        }
    }) as client:
        tools = client.get_tools()
        agent = create_react_agent(
            ChatOpenAI(model="gpt-4o"),
            tools,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Omie ERP, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

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.

LangChain's ecosystem of 500+ components combines seamlessly with Omie ERP through native MCP adapters. Connect 16 tools via the Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures — with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

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 LangChain 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 LangChain via MCP

Follow these steps to integrate the Omie ERP MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 16 tools from Omie ERP via MCP

Why Use LangChain with the Omie ERP MCP Server

LangChain provides unique advantages when paired with Omie ERP through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents — combine Omie ERP MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Omie ERP queries for multi-turn workflows

Omie ERP + LangChain Use Cases

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

RAG with live data: combine Omie ERP tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Omie ERP, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Omie ERP tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Omie ERP tool call, measure latency, and optimize your agent's performance

Omie ERP MCP Tools for LangChain (16)

These 16 tools become available when you connect Omie ERP to LangChain 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 LangChain

Ready-to-use prompts you can give your LangChain 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 LangChain

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

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Omie ERP + LangChain FAQ

Common questions about integrating Omie ERP MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.