Odoo MCP Server

Odoo MCP Server

An MCP server that enables AI assistants to interact with Odoo ERP apps like Inventory, CRM, Sales, and Manufacturing. It allows users to read, create, and manage Odoo records and workflows using natural language commands.

Category
Visit Server

README

Odoo MCP Server

MCP (Model Context Protocol) server for interacting with Odoo ERP. Enables AI assistants like Claude to read and write data across Odoo apps including Inventory, CRM, Sales, Manufacturing, and Purchases.

Repository: https://github.com/deeprunnerai/odoo-mcp-server

Quick Start

1. Clone and build

git clone https://github.com/deeprunnerai/odoo-mcp-server.git
cd odoo-mcp-server
npm install
npm run build

2. Configure Claude Code

Add to your Claude Code settings (~/.claude.json) under the mcpServers section.

Important: Replace the path with your actual clone location.

macOS/Linux:

{
  "mcpServers": {
    "odoo": {
      "type": "stdio",
      "command": "node",
      "args": ["/Users/YOUR_USERNAME/Projects/odoo-mcp-server/dist/index.js"],
      "env": {
        "ODOO_URL": "https://odoo.deeprunner.ai",
        "ODOO_DB": "deeprunner",
        "ODOO_USERNAME": "your-email@deeprunner.ai",
        "ODOO_PASSWORD": "your-password"
      }
    }
  }
}

Windows:

{
  "mcpServers": {
    "odoo": {
      "type": "stdio",
      "command": "node",
      "args": ["C:\\Users\\YOUR_USERNAME\\Projects\\odoo-mcp-server\\dist\\index.js"],
      "env": {
        "ODOO_URL": "https://odoo.deeprunner.ai",
        "ODOO_DB": "deeprunner",
        "ODOO_USERNAME": "your-email@deeprunner.ai",
        "ODOO_PASSWORD": "your-password"
      }
    }
  }
}

To find your path: After cloning, run pwd (macOS/Linux) or cd (Windows) in the odoo-mcp-server directory.

3. Restart Claude Code

After adding the config, restart Claude Code to load the MCP server.

Available Tools

Generic Tools

  • odoo_search - Search records in any model
  • odoo_read - Read specific records by ID
  • odoo_search_read - Search and read in one call
  • odoo_create - Create new records
  • odoo_update - Update existing records
  • odoo_delete - Delete records
  • odoo_get_fields - Get field definitions for a model
  • odoo_execute - Execute any model method

Inventory Tools

  • inventory_list_products - List products with stock info
  • inventory_get_stock - Get stock levels by product/warehouse
  • inventory_list_warehouses - List all warehouses
  • inventory_list_operations - List receipts/deliveries/transfers
  • inventory_create_transfer - Create internal stock transfer

CRM/Sales Tools

  • crm_list_leads - List CRM leads/opportunities
  • crm_create_lead - Create new lead
  • sales_list_orders - List sales orders
  • sales_create_order - Create sales order
  • sales_confirm_order - Confirm quotation

Contacts Tools

  • contacts_list - List partners/contacts
  • contacts_create - Create new contact

Manufacturing Tools

  • manufacturing_list_orders - List manufacturing orders
  • manufacturing_create_order - Create MO
  • manufacturing_list_boms - List Bills of Materials

Purchase Tools

  • purchase_list_orders - List purchase orders
  • purchase_create_order - Create PO

Example Usage

Once configured, you can ask Claude things like:

  • "List all products in the Air Quality Sensors category"
  • "What's the current stock of AethAir Pro 500 across all warehouses?"
  • "Create a sales order for Tesla with 10 units of the outdoor sensor"
  • "Show me all pending manufacturing orders"
  • "Create a new lead for a potential government contract"
  • "How many users are there in Odoo?"

Common Odoo Models

Model Description
product.product Product variants
product.template Product templates
stock.quant Stock quantities
stock.picking Inventory transfers
stock.warehouse Warehouses
res.partner Contacts/Partners
res.users Users
sale.order Sales orders
purchase.order Purchase orders
crm.lead CRM leads/opportunities
mrp.production Manufacturing orders
mrp.bom Bills of materials

Development

Run in development mode:

npm run dev

Build for production:

npm run build

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured