Odoo

Provides access to Odoo models, records, and methods via MCP for AI assistants.

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "willval117-mcp-to-odoo": {
      "command": "python",
      "args": [
        "-m",
        "odoo_mcp"
      ],
      "env": {
        "ODOO_DB": "your-database-name",
        "ODOO_URL": "https://your-odoo-instance.com",
        "HTTP_PROXY": "http://your-proxy.example.com",
        "ODOO_TIMEOUT": "30",
        "ODOO_PASSWORD": "your-password-or-api-key",
        "ODOO_USERNAME": "your-username",
        "ODOO_VERIFY_SSL": "true"
      }
    }
  }
}

You can connect your AI assistants to an Odoo ERP instance through an MCP server that exposes Odoo models, records, and methods. This enables natural language workflows to read, create, update, and search data in Odoo as part of your assistant’s capabilities, while keeping a clean request/response lifecycle and robust error handling.

How to use

Install and run the Odoo MCP Server locally or in your environment. Then configure your MCP client to connect to the server using either a local stdio command or a containerized (Docker) setup. Use the available tools to search, read, create, update, delete, or execute custom methods on Odoo models. You can also discover model fields and pattern-based resources to navigate Odoo data structures. For best results, provide clear model names, IDs, and field lists when performing operations.

How to install

Prerequisites you’ll need before installation: Python (for the Python-based MCP server) and Docker if you want to run the container version. You will also need network access to your Odoo instance and the necessary credentials.

Install the Python MCP package that provides Odoo MCP functionality.

pip install odoo-mcp

Run the server directly from the installed package or use development tooling if you are actively developing the MCP server code.

odoo-mcp

If you’re developing, you can run the server module directly with the MCP development tooling and include extra dependencies as needed.

mcp dev odoo_mcp/server.py

mcp dev odoo_mcp/server.py --with pandas --with numpy

mcp dev odoo_mcp/server.py --with-editable .

Additional steps for environments and configurations

You can also run the server via Docker by passing the Odoo connection details as environment variables and mounting the necessary settings for a local runtime.

Available tools

search_records

Search for records in a specified Odoo model using a domain, with optional fields and limit.

read_record

Read detailed information for a single record in a given model with optional fields.

create_record

Create a new record in a specified Odoo model and return the new record ID.

update_record

Update fields on an existing record in a specified Odoo model.

delete_record

Delete a record from a specified Odoo model.

execute_method

Invoke a custom method on an Odoo model with optional positional and keyword arguments.

get_model_fields

Retrieve field definitions for a given Odoo model.

search_employee

Search for employees by name with an optional result limit.

search_holidays

Find holidays within a given date range, optionally filtered by employee.

Built by

VeilStrat

AI signals for GTM teams