
mcp-server-odoo
by ivnvxd·★ 282·Score 52
MCP server enabling AI assistants to securely interact with Odoo ERP systems for data retrieval and manipulation.
Overview
This MCP server provides a robust interface between AI assistants and Odoo ERP systems, offering comprehensive tools for data operations. It supports multiple authentication methods (API keys or username/password), provides fine-grained access controls, and includes both standard security mode and a YOLO mode for development. The server implements various capabilities including record search, creation, updates, deletion, counting, model inspection, server-side aggregation, and workflow actions. It features LLM-optimized output formatting, smart field selection, multi-language support, and pagination for large datasets.
Try asking AI
After installing, here are 3 things you can ask your AI assistant:
When to choose this
Choose this MCP server if you need to integrate AI assistants with an existing Odoo ERP system for data retrieval, manipulation, and workflow automation.
When NOT to choose this
Avoid if you don't use Odoo, as this server is specifically designed for Odoo integration. Also avoid YOLO mode in production environments due to security risks.
Tools this server exposes
8 tools extracted from the READMEsearch_recordsSearch and retrieve Odoo records matching specific criteria
create_recordCreate new records in Odoo with field validation
update_recordUpdate existing data in Odoo records
delete_recordDelete Odoo records respecting model permissions
count_recordsCount records matching specific criteria without retrieving data
inspect_modelInspect model fields to understand data structure
aggregate_recordsPerform server-side aggregation (group, sum, count)
call_model_methodInvoke public Odoo methods (requires YOLO mode)
Comparable tools
Installation
Installation
Prerequisites
- Python 3.10 or higher
- Access to an Odoo instance
Install UV First
The MCP server runs on your local computer (where Claude Desktop is installed), not on your Odoo server. You need to install UV on your local machine.
Installing via MCP Settings (Recommended)
Add this configuration to your MCP settings:
{
"mcpServers": {
"odoo": {
"command": "uvx",
"args": ["mcp-server-odoo"],
"env": {
"ODOO_URL": "https://your-odoo-instance.com",
"ODOO_API_KEY": "your-api-key-here"
}
}
}
}For Claude Desktop, add to ~/Library/Application Support/Claude/claude_desktop_config.json
Compare mcp-server-odoo with
Last updated · Auto-generated from public README + GitHub signals.