AI-OdooFinder
Allows AI agents to search Odoo modules across OCA repositories using hybrid search (semantic + full-text) with version filtering.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AI-OdooFinderfind an Odoo 17 module for inventory management"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI-OdooFinder
Find the perfect Odoo module with AI in seconds.
An MCP (Model Context Protocol) server that enables LLMs to search Odoo modules in OCA repositories using hybrid search (semantic + full-text).
The Problem
As an Odoo developer:
You build features that already exist in OCA
You spend hours searching for the right module on GitHub
You install modules incompatible with your version
You discover abandoned modules after integration
Related MCP server: Marcus Local MCP Server
The Solution
AI-OdooFinder provides:
Hybrid Search: Combines semantic search (embeddings) with BM25 full-text
Version Filtering: Only shows compatible modules (12.0 to 19.0)
AI Enrichment: Descriptions, tags and keywords generated by Grok-4-fast
MCP Integration: Use it from Claude, ChatGPT, Cursor, VS Code, Zed... via a public URL
Architecture
┌──────────────────────────┐ ┌───────────────────────────────────────┐
│ Claude.ai / Desktop │ │ Eticco infrastructure (Docker) │
│ Claude Code · ChatGPT │ HTTPS │ ┌──────────────┐ ┌─────────────┐ │
│ Cursor · VS Code · Zed │────────►│ │ MCP Server │──►│ FastAPI │ │
│ Windsurf · ... │ │ │ (Streamable │ │ backend │ │
└──────────────────────────┘ │ │ HTTP) │ └──────┬──────┘ │
https://addon-finder.eticco.es │ └──────────────┘ │ │
│ ┌──────▼──────┐ │
│ │ PostgreSQL │ │
│ │ + pgvector │ │
│ └─────────────┘ │
└───────────────────────────────────────┘Usage modes:
Remote MCP (recommended): Point any MCP client to
https://addon-finder.eticco.es— nothing to installLocal MCP (STDIO): The PyPI package runs locally against your own backend (self-hosting)
Components:
MCP Server (Streamable HTTP): public endpoint for MCP clients
FastAPI Backend: hybrid search engine (internal)
PostgreSQL + pgvector: 19,700+ modules with embeddings
Public instance hosted by Eticco. Search over OCA community modules is open, no login required. Eticco is also extending the service with its own internal modules; that part requires authentication and is for internal use only.
Statistics
Metric | Value |
Indexed Modules | 19,700+ |
Odoo Versions | 8 (12.0 – 19.0) |
With AI Enrichment | 100% |
Installation
No installation needed. AI-OdooFinder is available as a public remote MCP server:
https://addon-finder.eticco.esTransport | Streamable HTTP |
Authentication | None for OCA community modules |
Tool |
|
Add that URL to your MCP client (see below). If your client only supports local STDIO servers, use the mcp-remote bridge (requires Node.js):
{
"mcpServers": {
"ai-odoofinder": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://addon-finder.eticco.es"]
}
}
}IDE/Client Configuration
Go to Settings > Connectors
Click "Add custom connector"
Enter the MCP server URL:
https://addon-finder.eticco.esSave and start searching
Custom connectors are shared between Claude.ai and Claude Desktop. On older Desktop versions without connectors, use the
mcp-remoteconfig above inclaude_desktop_config.json.
claude mcp add --transport http ai-odoofinder https://addon-finder.eticco.esUsage:
claude
> I need an Odoo 17 module for subscriptionsGo to Settings > Apps & Connectors > Advanced and enable Developer Mode
Create a new connector with URL
https://addon-finder.eticco.esAuthentication: None
Usage:
Use ai-odoofinder to find Odoo 17 modules for inventoryCreate .vscode/mcp.json (project) or add it to your user mcp.json:
{
"servers": {
"ai-odoofinder": {
"type": "http",
"url": "https://addon-finder.eticco.es"
}
}
}For Business/Enterprise: Admin must enable the "MCP servers in Copilot" policy.
Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"ai-odoofinder": {
"url": "https://addon-finder.eticco.es"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"ai-odoofinder": {
"serverUrl": "https://addon-finder.eticco.es"
}
}
}Add to ~/.config/zed/settings.json:
{
"context_servers": {
"ai-odoofinder": {
"url": "https://addon-finder.eticco.es"
}
}
}Use the mcp-remote bridge:
{
"mcpServers": {
"ai-odoofinder": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://addon-finder.eticco.es"]
}
}
}See full troubleshooting: MCP Client Configurations
The ai-odoofinder-mcp PyPI package runs the MCP server locally and talks to the FastAPI backend REST API. The public instance does not expose that REST API, so this mode is meant for your own deployment (see Deployment & Operations):
{
"mcpServers": {
"ai-odoofinder": {
"command": "uvx",
"args": ["ai-odoofinder-mcp"],
"env": {
"AI_ODOOFINDER_API_URL": "http://localhost:8989"
}
}
}
}Requires uv.
Full configuration guide: MCP Client Configurations
Client Compatibility Matrix
Client | Remote URL | Via | Notes |
Claude.ai Web | ✅ | — | Custom connector |
Claude Desktop | ✅ | ✅ | Connector or bridge |
Claude Code CLI | ✅ | ✅ |
|
ChatGPT Dev Mode | ✅ | — | Developer Mode |
VS Code Copilot | ✅ | ✅ |
|
Cursor | ✅ | ✅ | |
Windsurf | ✅ | ✅ |
|
Zed | ✅ | ✅ | |
Antigravity | ⚠️ | ✅ | Use the bridge |
Full details: See MCP Client Configurations
Deploy Your Own Instance
See docs/en/DEPLOYMENT_OPERATIONS.md for Docker deployment instructions.
Usage
Once connected, simply ask in natural language:
"I need a module for Odoo 17 that handles recurring payments"Your assistant will call search_odoo_modules and show compatible OCA modules with their repository, summary and GitHub link.
Check the service status:
curl https://addon-finder.eticco.es/healthThe FastAPI REST API (
/search,/stats) is only exposed in self-hosted deployments (http://localhost:8989).
Tech Stack
Component | Technology |
Backend | FastAPI (Python 3.14) |
Database | PostgreSQL 17 + pgvector |
Embeddings | Qwen3-Embedding-4B via OpenRouter |
Enrichment | Grok-4-fast via OpenRouter |
MCP Server | FastMCP (Python) |
Containers | Docker + Docker Compose |
Hosting | Eticco infrastructure (Docker + nginx) |
Documentation
Interactive Showcase - Visual presentation of the project
MCP Client Configurations - Complete guide for all MCP clients
Deployment & Operations - Deployment and operations guide
Project History - Evolution of the project architecture
Changelog - Change history
MCP Server README - MCP server installation and configuration
Development
Requirements
Python 3.14+
uv (dependency manager)
Docker (for local PostgreSQL)
Local Setup
# Clone
git clone https://github.com/SantipBarber/ai-odoo-finder.git
cd ai-odoo-finder
# Install dependencies
uv sync
# Configure variables
cp .env.example .env
# Edit .env with your credentials
# Start PostgreSQL
docker compose up -d db
# Run ETL (index modules)
uv run python scripts/etl_oca_modules.py
# Start API
uv run uvicorn backend.app.main:app --port 8989License
MIT - See LICENSE
Author
Santiago Pérez Barber
GitHub: @SantipBarber
LinkedIn: santipbarber
Acknowledgments
Odoo Community Association (OCA) - For their open source work
Anthropic - For Claude and the MCP protocol
This server cannot be deployed
Maintenance
Related MCP Connectors
Search your knowledge bases from any AI assistant using hybrid RAG.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Search indexed code, trace dependencies, assess change impact, and recall repository memory.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to index and search codebases using semantic search powered by multiple embedding providers (OpenAI, VoyageAI, Gemini, Ollama) and vector database storage.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to semantically search through indexed documentation websites and local code repositories using OpenAI embeddings and ChromaDB vector storage.-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform semantic, hybrid, and filtered search on indexed local documentation with RAG capabilities.2MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to search and query documentation from git repositories using hybrid search and structured metadata queries.1-