Odoo XML-RPC MCP Server
Interact with Odoo instances using the XML-RPC API. Requires configuration via environment variables or config files.
Odoo XML-RPC MCP Server
A Model Context Protocol (MCP) server that provides tools for interacting with Odoo via XML-RPC.
Features
- Connect to any Odoo instance via XML-RPC
- Configurable project and environment parameters
- Environment variable support with priority over config files
- Complete set of Odoo operations: search, read, create, write, delete
- Integration with Claude Desktop and Claude Code
Installation
Global Installation (Desktop MCP Server)
- Install globally using npm:
npm install -g .
- Add to your Claude Desktop configuration (
~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"odoo-xmlrpc": {
"command": "odoo-xmlrpc-mcp-server",
"args": ["--project", "your_project", "--environment", "your_env"],
"env": {
"ODOO_URL": "https://your-odoo.domain.com",
"ODOO_DATABASE": "your_database",
"ODOO_USERNAME": "your_username",
"ODOO_PASSWORD": "your_password"
}
}
}
}
Local Installation (Claude Code)
-
Clone or copy this repository to your project directory
-
Install dependencies:
npm install
- Build the project:
npm run build
- Create
.claude.jsonin your project root:
{
"mcp": {
"servers": {
"odoo-xmlrpc": {
"command": "node",
"args": ["./dist/index.js", "--project", "your_project", "--environment", "your_env"],
"env": {
"ODOO_URL": "https://your-odoo.domain.com",
"ODOO_DATABASE": "your_database",
"ODOO_USERNAME": "your_username",
"ODOO_PASSWORD": "your_password"
}
}
}
}
}
Development
For development, you can run directly with tsx:
npm run dev -- --project your_project --environment your_env
Configuration
Config File Method
Create a configuration file at ~/.odoo_config/<project>_<environment>.conf:
[odoo]
url = https://your-odoo.domain.com
database = your_database
username = your_username
password = your_password
Environment Variables (Priority)
Set these environment variables (they take priority over config files):
ODOO_URLODOO_DATABASEODOO_USERNAMEODOO_PASSWORD
Usage
Available Tools
odoo_search
Search for records in an Odoo model.
{
"model": "res.partner",
"domain": [["is_company", "=", true]],
"limit": 10
}
odoo_read
Read specific records by ID.
{
"model": "res.partner",
"ids": [1, 2, 3],
"fields": ["name", "email", "phone"]
}
odoo_create
Create a new record.
{
"model": "res.partner",
"values": {
"name": "New Company",
"is_company": true,
"email": "[email protected]"
}
}
odoo_write
Update existing records.
{
"model": "res.partner",
"ids": [123],
"values": {
"phone": "+1-555-0123"
}
}
odoo_unlink
Delete records.
{
"model": "res.partner",
"ids": [456]
}
odoo_search_count
Count records matching a domain.
{
"model": "res.partner",
"domain": [["is_company", "=", true]]
}
odoo_fields_get
Get field definitions for a model.
{
"model": "res.partner",
"fields": ["name", "email"]
}
odoo_search_read
Search and read in one operation.
{
"model": "res.partner",
"domain": [["is_company", "=", true]],
"fields": ["name", "email"],
"limit": 5
}
Development
Requirements
- Node.js 18+
- npm or yarn
Running Locally
npm run dev -- --project myproject --environment staging
Building
npm run build
Testing Connection
npm run dev -- --project idp --environment staging
License
MIT License
Servidores relacionados
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
DocsFetcher
Fetches package documentation from various language ecosystems without requiring API keys.
Terraform MCP
A command-line tool that acts as an MCP server to interact with Terraform environments.
Image
Fetch and process images from URLs, local file paths, and numpy arrays, returning them as base64-encoded strings.
Sleep MCP Server
Provides a sleep/wait tool to add delays between operations, such as waiting between API calls or testing eventually consistent systems.
IBM wxflows
Tool platform by IBM to build, test and deploy tools for any data source
Srclight
Deep code indexing for AI agents — 25 MCP tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages. Fully local, zero cloud dependencies.
App Market Intelligence MCP
Analyze app data from the Apple App Store and Google Play Store for market intelligence and insights.
Ai Notify MCP
Receive system notifications in your code editor when an AI response is complete.
APIWeaver
A universal bridge to convert any web API into an MCP server, supporting multiple transport types.
Vibe-Coder
A server for a structured, LLM-based coding workflow, from feature clarification and planning to phased development and progress tracking.