mcp-odoo
MCP Server for Odoo
claude mcp add --transport stdio tuanle96-mcp-odoo python -m odoo_mcp \ --env ODOO_DB="your-database-name" \ --env ODOO_URL="https://your-odoo-instance.com" \ --env ODOO_PASSWORD="your-password-or-api-key" \ --env ODOO_USERNAME="your-username"
How to use
This MCP server provides a bridge between AI agents and your Odoo ERP using the Odoo MCP implementation. It exposes tools to run custom methods on Odoo models, search for employees, and search holidays within a date range. The server communicates with Odoo via XML-RPC, allowing stateless request/response cycles and clear error messaging. Use the included tools to perform common ERP actions from your assistant, such as invoking model methods, retrieving lists of employees, or checking holiday schedules. The Resources section documents how you can query available models, specific model metadata, individual records, and domain-based searches. To run the server, configure Odoo connection details either via a config file (odoo_config.json) or environment variables, then start the MCP server using the chosen integration method (Python module, or Docker).
How to install
Prerequisites:
- Python 3.8+ installed on your system
- Access to an Odoo instance (XML-RPC enabled)
- Optional: Docker if you prefer containerized deployment
Install the Python MCP package and dependencies:
pip install odoo-mcp
Run the server directly from the installed package:
odoo-mcp
Alternative: run with MCP development tools (for debugging/development):
mcp dev odoo_mcp/server.py
If you prefer Docker:
docker build -t mcp/odoo:latest -f Dockerfile .
Configuration examples (refer to README for full details):
- Python environment-based setup (odoo_mcp):
# Ensure environment variables are set
export ODOO_URL=https://your-odoo-instance.com
export ODOO_DB=your-database-name
export ODOO_USERNAME=your-username
export ODOO_PASSWORD=your-password-or-api-key
odoo-mcp
- Docker-based setup (mcp/odoo):
docker run -i --rm \
-e ODOO_URL=$ODOO_URL \
-e ODOO_DB=$ODOO_DB \
-e ODOO_USERNAME=$ODOO_USERNAME \
-e ODOO_PASSWORD=$ODOO_PASSWORD \
mcp/odoo
Configuration files (example): od odoo_config.json and claude_desktop_config.json as shown in the README will wire the MCP server into Claude Desktop or other tooling.
Additional notes
Tips and notes:
- Use the ODOO_TIMEOUT and ODOO_VERIFY_SSL environment variables to tune connection behavior and SSL verification.
- If you run behind a proxy, set HTTP_PROXY and HTTPS_PROXY accordingly.
- The Domain and Fields parameter formatting guidelines described in the README will help you construct valid inputs for searches and method calls.
- For development, mounting local code with --with-editable . can speed iteration when using the Python server variant.
- Ensure the Odoo instance is accessible from the MCP host; firewalls or VPNs may require additional networking configuration.
- When using Docker, remember to pass sensitive credentials through environment variables rather than inline in command lines when possible.
Related MCP Servers
MCP-Bridge
A middleware to provide an openAI compatible endpoint that can call MCP tools
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
mcp -memos-py
A Python package enabling LLM models to interact with the Memos server via the MCP interface for searching, creating, retrieving, and managing memos.
cbi
CB Insights' MCP Server
mcp-link
Local MCP server with included tools, that runs on Windows, Mac, and Linux