Woolworths MCP Server

Woolworths MCP Server

Enables interaction with Woolworths Australia's online shopping platform through browser automation and API integration. Supports product search, browsing specials, managing shopping cart, and accessing product details through natural language.

Category
访问服务器

README

Woolworths MCP Server

A Model Context Protocol (MCP) server for interacting with Woolworths Australia's online shopping platform. This server provides tools for browsing products, searching items, viewing specials, and more.

Features

  • Browser Automation: Uses Puppeteer to open a browser, navigate to Woolworths, and capture session cookies
  • Session Management: Maintains session cookies for authenticated API requests
  • Product Search: Search for products across the Woolworths catalog with filtering and sorting
  • Product Details: Get detailed information about specific products
  • Specials & Deals: Browse current specials and promotional offers
  • Category Browsing: Explore product categories
  • Shopping Cart: Add items to cart, view cart contents, update quantities, and remove items

Installation

  1. Install dependencies:
npm install
  1. Build the TypeScript code:
npm run build

Usage

Running the Server

The MCP server runs on stdio and is designed to be used with MCP-compatible clients (like Claude Desktop, Cline, or other AI assistants).

npm start

Configuration for Claude Desktop

Add this to your Claude Desktop configuration file:

Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "woolworths": {
      "command": "node",
      "args": ["C:\\Users\\eglass\\Projects\\Woolworths\\dist\\index.js"]
    }
  }
}

Make sure to update the path to match your installation directory.

Available Tools

1. woolworths_open_browser

Opens a browser and navigates to the Woolworths website. This is typically the first step to establish a session.

Parameters:

  • headless (boolean, optional): Whether to run in headless mode (default: false)

Example:

{
  "headless": false
}

2. woolworths_navigate

Navigate to a specific URL on the Woolworths website.

Parameters:

  • url (string, required): The URL to navigate to

3. woolworths_get_cookies

Retrieves and stores session cookies from the current browser session. Run this after logging in or when you have an active session.

Parameters: None

4. woolworths_close_browser

Closes the browser instance while preserving the captured session cookies.

Parameters: None

5. woolworths_search_products

Search for products on Woolworths.

Parameters:

  • searchTerm (string, required): The product search term
  • pageSize (number, optional): Number of results to return (default: 20)

Example:

{
  "searchTerm": "milk",
  "pageSize": 20
}

6. woolworths_get_product_details

Get detailed information about a specific product by its stockcode.

Parameters:

  • stockcode (string, required): The product stockcode/ID

7. woolworths_get_specials

Get current specials and deals from Woolworths.

Parameters:

  • category (string, optional): Category filter (e.g., 'fruit-veg', 'meat-seafood')
  • pageSize (number, optional): Number of results to return (default: 20)

8. woolworths_get_categories

Get the list of available product categories.

Parameters: None

9. woolworths_add_to_cart

Add a product to the shopping cart/trolley.

Parameters:

  • stockcode (number, required): The product stockcode/ID
  • quantity (number, optional): Quantity to add (default: 1)

Example:

{
  "stockcode": 123456,
  "quantity": 2
}

10. woolworths_get_cart

Get the current contents of the shopping cart/trolley.

Parameters: None

11. woolworths_remove_from_cart

Remove a product from the shopping cart/trolley.

Parameters:

  • stockcode (number, required): The product stockcode/ID to remove

12. woolworths_update_cart_quantity

Update the quantity of a product in the shopping cart/trolley.

Parameters:

  • stockcode (number, required): The product stockcode/ID
  • quantity (number, required): New quantity

Typical Workflow

  1. Open Browser: Use woolworths_open_browser to launch a browser window
  2. Log In (if needed): The browser will open in non-headless mode by default, allowing you to manually log in to your Woolworths account if required
  3. Capture Cookies: Use woolworths_get_cookies to capture session cookies
  4. Close Browser: Use woolworths_close_browser to close the browser (cookies are preserved)
  5. Use API Tools: Now you can use any of the API tools (search, get product details, etc.)

Example Usage Scenario

1. User: "Open the Woolworths browser"
   → Calls: woolworths_open_browser
   
2. User manually logs in on the opened browser (if needed)

3. User: "Get the session cookies"
   → Calls: woolworths_get_cookies
   
4. User: "Close the browser"
   → Calls: woolworths_close_browser
   
5. User: "Search for bananas"
   → Calls: woolworths_search_products with searchTerm="bananas"
   
6. User: "What are the current specials?"
   → Calls: woolworths_get_specials

7. User: "Add product 123456 to my cart"
   → Calls: woolworths_add_to_cart with stockcode=123456

8. User: "Show me my cart"
   → Calls: woolworths_get_cart

Technical Details

Browser Automation

The server uses Puppeteer to:

  • Launch a Chromium browser instance
  • Navigate to Woolworths website
  • Capture cookies from the browser session
  • Maintain user agent and browser fingerprint

API Integration

Once cookies are captured, the server makes authenticated requests to Woolworths' internal APIs:

  • Search API: /apis/ui/Search/products (POST)
  • Product Detail API: /apis/ui/product/detail/{stockcode}
  • Browse/Category API: /apis/ui/browse/category
  • Categories API: /apis/ui/PiesCategoriesWithSpecials
  • Shopping Cart API: /apis/ui/Trolley/* (AddItem, RemoveItem, UpdateItem, Get)

Session Management

Session cookies are stored in memory for the duration of the server process. If the server restarts, you'll need to recapture cookies by opening the browser again.

Development

Watch Mode

For development with auto-recompilation:

npm run dev

Building

npm run build

Requirements

  • Node.js 18 or higher
  • npm or yarn
  • Chromium/Chrome (automatically installed by Puppeteer)

Notes

  • The browser opens in non-headless mode by default to allow for manual login
  • Session cookies are stored in memory and persist until the server is restarted
  • API endpoints are based on Woolworths' public web interface and may change
  • Always respect Woolworths' Terms of Service when using this tool

Troubleshooting

Browser won't open

  • Check that Puppeteer installed correctly
  • Try running with headless: true if display issues occur

API requests fail

  • Ensure you've captured cookies with woolworths_get_cookies
  • Check that the session hasn't expired (you may need to re-open browser and capture new cookies)
  • Verify the API endpoints are still valid

Connection issues

  • Ensure you have a stable internet connection
  • Check that Woolworths website is accessible from your location

License

MIT

Disclaimer

This is an unofficial tool and is not affiliated with or endorsed by Woolworths Group Limited. Use at your own risk and ensure compliance with Woolworths' Terms of Service.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选