mcp-server-odoo

mcp-server-odoo

An extensible MCP server that integrates Odoo with LLMs to enable querying and managing business data like partners, quotations, and sales orders. It supports custom tool registration and multiple transport protocols for both local and remote communication.

Category
Visit Server

README

mcp-server-odoo

An extensible Model Context Protocol server that provides integration between Odoo and LLMs.

Beware: the project is in very early development. Expect rough edges. We welcome any feedback!

MCP server in action

Here's a demonstration of what kind of capabilities the MCP enables in Claude for Desktop:

MCP in action

Prerequisites

Configuration

The server looks for the following variables in the execution environment:

Variable Required Description Example
ODOO_BASE_URL Yes The URL of the Odoo instance http://localhost:8069
ODOO_DATABASE Yes The database name to connect to mydatabase
ODOO_USERNAME Yes Username for authentication admin
ODOO_PASSWORD Yes Password or API Key for authentication admin
ODOO_VERSION Yes Major version of your Odoo server 18
LOG_LEVEL No Desided logging level (see Python logging levels), default is INFO INFO
TRANSPORT_PROTOCOL Yes The MCP transport protocol to use. Valid values are stdio for local-only communication or sse / streamable-http for remote communication stdio
HOST No The IP address(es) on which the server is to listen for connections from clients 127.0.0.1
TOOLS_TO_REGISTER Yes Comma-separated list of tools to expose to the MCP client. Tools can be chosen from those included within this project (see directory src/mcp_server_odoo/tools), or custom ones provided by external files (see EXT_DIRECTORIES) search_partners,search_quotations,search_sales_orders,search_customer_invoices
EXT_DIRECTORIES No Comma-separated list of paths to search for additional tools that can be loaded at runtime /your/custom/path

Installation

Install the tool with uv tool:

uv tool install --from git+https://github.com/alberto-re/mcp-server-odoo mcp-server-odoo

Run the server

Execute it directly with uvx:

uvx mcp-server-odoo

Run within Docker

A Dockerfile is included if you wish to run the MCP server inside a Docker container.

To build the container execute this command from the root directory of the repository:

docker build -t mcp-server-odoo .

Now you can execute the container from the built image with:

docker run --rm --env-file /path/to/env/file -p 8000:8000 mcp-server-odoo

When running inside a container remember to use an HTTP based transport protocol (i.e. set TRANSPORT_PROTOCOL to sse or streamable-http) and to make the server listen to all interfaces (i.e. set HOST to 0.0.0.0).

Integrations

Connecting to Claude Desktop

  1. Edit the Claude for Desktop configuration file.
  • In MacOS the configuration is located at ~/Library/Application Support/Claude/claude_desktop_config.json.
  • In Windows the configuration is located at %APPDATA%\Claude\claude_desktop_config.json
  1. Add the server configuration under the mcpServers section.
{
  "mcpServers": {
    "mcp-server-odoo": {
      "command": "uvx",
      "args": [
        "mcp-server-odoo"
      ],
      "env": {
        "ODOO_BASE_URL": "http://localhost:8069",
        "ODOO_DATABASE": "mydatabase",
        "ODOO_USERNAME": "admin",
        "ODOO_PASSWORD": "admin",
        "ODOO_VERSION": "18",
        "TRANSPORT_PROTOCOL": "stdio",
        "TOOLS_TO_REGISTER": "search_partners,search_quotations,search_sales_orders,search_customer_invoices"
      }
    }
  }
}
  1. Restart Claude for Desktop.

Connecting to mcphost

  1. Edit the mcphost configuration file. See the documentation for where it looks for configuration files.

  2. Add the server configuration under the mcpServers section.

{
  "mcpServers": {
    "mcp-server-odoo": {
      "command": "uvx",
      "args": [
        "mcp-server-odoo"
      ],
      "env": {
        "ODOO_BASE_URL": "http://localhost:8069",
        "ODOO_DATABASE": "mydatabase",
        "ODOO_USERNAME": "admin",
        "ODOO_PASSWORD": "admin",
        "ODOO_VERSION": "18",
        "TRANSPORT_PROTOCOL": "stdio",
        "TOOLS_TO_REGISTER": "search_partners,search_quotations,search_sales_orders,search_customer_invoices"
      }
    }
  }
}
  1. Execute the mcphost command.

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