This server provides an MCP (Model Context Protocol) interface to interact with Odoo 19 ERP systems via its JSON-2 API, enabling AI assistants to query and manipulate Odoo data.

Model Discovery & Schema Inspection

• list_models: Browse all available Odoo models with optional name filtering

• get_fields: Inspect field metadata (types, labels, required/readonly flags, relations, etc.) for any model

Data Querying

• search_records: Query records using Odoo domain syntax with filtering, sorting, pagination, and Odoo 19+ any operator support

• count_records: Count records matching a domain without fetching data

• read_records: Fetch specific records by ID (includes direct browser URL links)

Data Manipulation

• create_record: Create single or multiple records in any model

• update_record: Update one or more records by ID

• delete_record: Delete records via a mandatory two-step confirmation flow

• execute_method: Call arbitrary methods on any model (e.g., confirm orders, trigger workflows)

Resources (Dynamic Context)

• odoo://user / odoo://company: Current user and company info

• odoo://models: All available models

• odoo://model/{model_name}: Field definitions for a model

• odoo://record/{model_name}/{record_id}: A single record

Safety & Security

• READONLY_MODE=true hides all write tools from the LLM entirely (including execute_method for write operations)

• Delete operations require explicit user confirmation

• Sensitive fields (binary/image/HTML) are automatically filtered

• API key authentication for Odoo access

Deployment & Integration

• Supports stdio (local), http, and sse transport modes

• Docker/Docker Compose support for cloud deployment

• Compatible with Claude Code, Gemini CLI, and MCP Inspector

• /health endpoint for monitoring in HTTP/SSE modes

Enables interaction with Odoo 19 instances via the JSON-2 API, allowing users to search, create, read, update, and delete records across various models, as well as access system metadata, model definitions, and user/company information.

flowchart TB
 subgraph Client["MCP Client"]
 CC[Claude Code]
 GC[Gemini CLI]
 MI[MCP Inspector]
 end

 subgraph Server["MCP Server (FastMCP)"]
 R[Resources<br/>odoo://models<br/>odoo://user<br/>odoo://company]
 T[Tools<br/>search_records<br/>create_record<br/>update_record]
 DI[Dependency Injection<br/>get_shared_client]
 end

 subgraph RPC["OdooJsonRpcClient"]
 OL[odoolib<br/>json2/json2s protocol]
 end

 subgraph Odoo["Odoo Server"]
 EP["/jsonrpc endpoint"]
 end

 Client -->|MCP Protocol<br/>stdio/http/sse| Server
 R --> DI
 T --> DI
 DI --> RPC
 RPC -->|HTTP/HTTPS| Odoo

odoo://user → "我是誰"
odoo://company → "我在哪間公司"
odoo://models → "有哪些模型可用"

search_records(model="res.partner", domain=[...]) → 搜尋
create_record(model="sale.order", values={...}) → 建立

# ❌ Default Prompt（寫死）
SYSTEM_PROMPT = "當前用戶: Admin" # 換人登入就錯了

# ✅ Resource（動態）
@mcp.resource("odoo://user")
def get_current_user():
 return client.read("res.users", [uid]) # 即時查詢

cp .env.example .env

pip install -r requirements.txt

fastmcp dev inspector odoo_mcp_server.py

┌─────────────────────────────────────┐
│ 你的電腦 💻 │
│ │
│ Claude Desktop ──> MCP Server │
│ (使用本機算力) │
└─────────────────────────────────────┘

┌──────────────┐ ┌──────────────────┐
│ 你的電腦 │ │ 雲端 ☁️ │
│ │ │ │
│Claude Desktop│ ──網路──>│ MCP Server │
│ (輕量) │ │ (使用雲端算力) │
└──────────────┘ └──────────────────┘

# stdio 模式（預設）
python odoo_mcp_server.py

# HTTP 模式
python odoo_mcp_server.py --transport http --host 0.0.0.0 --port 8000

# SSE 模式（已棄用，建議使用 HTTP）
python odoo_mcp_server.py --transport sse --host 0.0.0.0 --port 8000

cp .env.example .env # 填入 ODOO_URL / ODOO_DATABASE / ODOO_API_KEY
cp docker-compose.example.yml docker-compose.yml # 依需求調整
docker compose up -d

volumes:
 shared-uploads:

services:
 odoo-mcp:
 build: .
 command: ["python", "odoo_mcp_server.py", "--transport", "http", "--host", "0.0.0.0", "--port", "8000"]
 # 對外暴露 port 8000（host 端 client 可直接連 http://localhost:8000/mcp）。
 # 若只需 Docker 內網存取（例如 client 也在同一個 compose 裡），可整段移除 ports。
 ports:
 - "8000:8000"
 environment:
 - ODOO_URL=${ODOO_URL}
 - ODOO_DATABASE=${ODOO_DATABASE}
 - ODOO_API_KEY=${ODOO_API_KEY}
 - READONLY_MODE=${READONLY_MODE:-false}
 volumes:
 - shared-uploads:/shared # 圖片傳遞通道；對應 Dockerfile 預建的 /shared/uploads
 restart: unless-stopped

claude mcp add --transport http odoo-mcp https://your-cloud-server.com:8000/mcp

{
 "mcpServers": {
 "odoo-mcp": {
 "type": "http",
 "url": "https://your-cloud-server.com:8000/mcp"
 }
 }
}

docker build -t odoo-mcp-server .

claude mcp add odoo-mcp-server -- python odoo_mcp_server.py

{
 "mcpServers": {
 "odoo-mcp-server": {
 "command": "/bin/python",
 "args": [
 "odoo_mcp_server.py"
 ]
 }
 }
}

claude mcp add odoo-mcp-server -- docker run -i --rm --add-host=host.docker.internal:host-gateway -e ODOO_URL=http://host.docker.internal:8069 -e ODOO_DATABASE=odoo19 -e ODOO_API_KEY=your_api_key_here odoo-mcp-server

{
 "mcpServers": {
 "odoo-mcp-server": {
 "command": "docker",
 "args": [
 "run",
 "-i",
 "--rm",
 "--add-host=host.docker.internal:host-gateway",
 "-e",
 "ODOO_URL=http://host.docker.internal:8069",
 "-e",
 "ODOO_DATABASE=odoo19",
 "-e",
 "ODOO_API_KEY=your_api_key_here",
 "odoo-mcp-server"
 ]
 }
 }
}

claude mcp add odoo-mcp-server -- docker run -i --rm --network host -e ODOO_URL=http://localhost:8069 -e ODOO_DATABASE=odoo19 -e ODOO_API_KEY=your_api_key_here odoo-mcp-server

{
 "mcpServers": {
 "odoo-mcp-server": {
 "command": "docker",
 "args": [
 "run",
 "-i",
 "--rm",
 "--network",
 "host",
 "-e",
 "ODOO_URL=http://localhost:8069",
 "-e",
 "ODOO_DATABASE=odoo19",
 "-e",
 "ODOO_API_KEY=your_api_key_here",
 "odoo-mcp-server"
 ]
 }
 }
}

claude mcp add odoo-mcp-server -- docker run -i --rm -e ODOO_URL=https://example.com/ -e ODOO_DATABASE=odoo19 -e ODOO_API_KEY=your_api_key_here odoo-mcp-server

{
 "mcpServers": {
 "odoo-mcp-server": {
 "command": "docker",
 "args": [
 "run",
 "-i",
 "--rm",
 "-e",
 "ODOO_URL=https://example.com/",
 "-e",
 "ODOO_DATABASE=odoo19",
 "-e",
 "ODOO_API_KEY=your_api_key_here",
 "odoo-mcp-server"
 ]
 }
 }
}

gemini mcp add --scope user odoo-mcp docker -- run -i --rm --add-host=host.docker.internal:host-gateway -e ODOO_URL=http://host.docker.internal:8069 -e ODOO_DATABASE=odoo19 -e ODOO_API_KEY=your_api_key_here odoo-mcp-server

{
 "mcpServers": {
 "odoo-mcp": {
 "command": "docker",
 "args": [
 "run",
 "-i",
 "--rm",
 "--add-host=host.docker.internal:host-gateway",
 "-e",
 "ODOO_URL=http://host.docker.internal:8069",
 "-e",
 "ODOO_DATABASE=odoo19",
 "-e",
 "ODOO_API_KEY=your_api_key_here",
 "odoo-mcp-server"
 ]
 }
 }
}

# 請將 your-server-ip 換成你的 MCP server 位址
openclaw mcp set odoo-mcp '{"type":"http","url":"http://your-server-ip:8000/mcp"}'

{
 "mcp": {
 "servers": {
 "odoo-mcp": {
 "url": "http://your-server-ip:8000/mcp",
 "transport": "streamable-http"
 }
 }
 }
}

openclaw config set commands.mcp true

openclaw gateway restart

# server 是否註冊成功
openclaw mcp list
openclaw mcp show odoo-mcp

# /mcp 開關狀態（應回傳 true）
openclaw config get commands.mcp

codex mcp add odoo-mcp -- echo placeholder

[mcp_servers.odoo-mcp]
command = "echo"
args = ["placeholder"]

[mcp_servers.odoo-mcp]
url = "https://your-cloud-server.com:8000/mcp"

curl http://localhost:8000/health
# {"status": "healthy", "service": "odoo-mcp-server", "version": "1.0.0"}