Shopify Storefront MCP Server
Enables interaction with multiple Shopify stores simultaneously through the Storefront API. Supports product search, cart management, and store operations across configured Shopify stores through natural language.
README
Demo Shopify Storefront MCP Server
This is created as a demo for a proposal regarding Public MCP Servers on the OpenAI Community Platform
Multi-Store Support
This server now supports multiple Shopify stores simultaneously. You can configure up to multiple stores and switch between them using the storeId parameter in all tools.
Setup
Single Store Setup (Legacy)
cp .env.example .env
Multi-Store Setup (Recommended)
cp .env.stores.example .env
Then, replace the environment variables with your actual Shopify store credentials:
- Domain: Your Shopify store domain (e.g.,
your-store.myshopify.com) - Storefront Token: Shopify Storefront API Token
- Admin Token: Admin API access token (for advanced operations)
- API Key/Secret: Your app's API credentials
Store Configuration
Each store requires:
- Unique
storeId(used in tool calls) - Store name (for display purposes)
- Domain and access tokens
- Enable/disable flag
Running
# First terminal
npm build
npm start
Deployment of the Public Server
You can deploy the Express Server whereever you wish and then use https://your-domain.com/mcp instead of http://localhost:3000/mcp for the following examples to test the remote server.
Connecting via Claude Desktop
First run the MCP Server like above. Then add this to your Claude Desktop Config
{
"mcpServers": {
"demo-shopify-storefront-mcp-server": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"http://localhost:3000/mcp"
]
}
}
}
Available Tools
Multi-Store Tools
listStores- List all configured and enabled storesfindProducts- Search products in a specific storegetProductById- Get product details by IDcartCreate- Create a new cartcartLinesAdd- Add items to cartcartLinesUpdate- Update cart itemscartLinesRemove- Remove items from cartgetCart- Get cart details
Usage Examples
All tools (except listStores) require a storeId parameter:
{
"storeId": "europride",
"query": "perfume"
}
Available store IDs:
europride- EURO PRIDE storewifimoney- WIFI MONEY storesaderstore- SADERSTORE store
Manual Testing
# Second terminal
npx @modelcontextprotocol/inspector http://localhost:3000/mcp
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。