Superstore MCP Server

Superstore MCP Server

Enables interaction with Real Canadian Superstore to extract order history, browse products, and export purchase data. Supports authentication via bearer token and provides comprehensive order management and product discovery capabilities.

Category
访问服务器

README

Superstore MCP Server

An MCP server for Real Canadian Superstore that extracts orders and product data with authentication.

Features

  • Order Management: Full order history with item details, dates, prices, images
  • DirectAuth: Fast bearer token authentication (no browser needed)
  • Data Export: Export orders to CSV or JSON for analysis
  • Product Discovery: Browse categories and search products
  • Web Content: Fetch and parse web pages

Installation

Quick Install to Cursor

Install MCP Server

Note: Make sure Cursor is running before clicking the install button.

Manual Installation

# Run directly with npx
npx -y superstore-mcp@latest

# Or clone from GitHub
git clone https://github.com/ai-protocols/superstore-mcp.git
cd superstore-mcp
npm install
npm run build

Configuration

Add to your mcp.json:

{
  "superstore-mcp": {
    "command": "npx",
    "args": ["-y", "superstore-mcp@latest"],
    "env": {
      "SUPERSTORE_BEARER_TOKEN": "your-token-here"
    }
  }
}

Getting Your Bearer Token

  1. Log in to https://www.realcanadiansuperstore.ca
  2. Open DevTools (F12) → Application → Cookies → www.realcanadiansuperstore.ca
  3. Find AccessToken cookie and copy its value (starts with eyJ)
  4. Paste into SUPERSTORE_BEARER_TOKEN

Tokens expire after ~1 hour. Refresh by copying a new token from your browser.

Available Tools

Authentication

login - Authenticate session

{}

logout - End session

{}

check_auth_status - Check authentication state

{}

Orders

get_orders - Get order history

{
  "limit": 10,
  "offset": 0
}

get_order_details - Get full order with items

{
  "order_id": "531900014110869"
}

get_recent_orders - Filter orders by date

{
  "days": 90
}

export_orders_csv - Export to CSV

{
  "include_items": true,
  "filepath": "./orders.csv"
}

export_orders_json - Export to JSON

{
  "include_items": true,
  "filepath": "./orders.json"
}

Products

get_categories - Get all categories

{}

get_products - Get products from categories

{
  "category_ids": ["28251"],
  "max_pages_per_category": 1
}

get_category - Get single category

{
  "category_id": "28251"
}

get_product - Search for product

{
  "category_id": "28251",
  "product_name": "bread"
}

search_products - Search products (alias)

{
  "category_id": "28251",
  "product_name": "milk"
}

get_product_details - Get product details from URL

{
  "product_url": "https://www.realcanadiansuperstore.ca/..."
}

get_product_details_by_name - Search and get details

{
  "category_id": "28251",
  "product_name": "butter"
}

Web Utilities

fetch_txt - Fetch web page as text

{
  "url": "https://www.realcanadiansuperstore.ca"
}

parse_sitemap - Parse sitemap

{
  "sitemap_url": "https://www.realcanadiansuperstore.ca/sitemap_index.xml"
}

Example Usage

Export All Orders

// Login
await mcp.call("login", {});

// Export with full item details
await mcp.call("export_orders_csv", {
  "include_items": true,
});

Analyze Spending

// Get recent orders
const orders = await mcp.call("get_recent_orders", { "days": 90 });

// Get details for each
for (const order of orders.orders) {
  const details = await mcp.call("get_order_details", {
    "order_id": order.id,
  });
  console.log(`${order.id}: ${details.items.length} items`);
}

Architecture

  • DirectAuth: Uses bearer token from browser (recommended)
  • API Integration: Calls api.pcexpress.ca/pcx-bff with proper headers
  • Fallback Mode: Puppeteer browser automation if no bearer token provided
  • HTML Parsing: JSDOM for product pages

Documentation

License

MIT

Disclaimer

Unofficial tool. Not affiliated with Loblaw Companies or Real Canadian Superstore. Use responsibly.


Repository: https://github.com/ai-protocols/superstore-mcp
Version: 2.0.0

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