Bring! Shopping MCP Server

Bring! Shopping MCP Server

Enables interaction with Bring! shopping lists through natural language, allowing users to manage shopping items, lists, and collaborate with other users via the unofficial Bring! API.

Category
访问服务器

README

MCP Server for Bring! Shopping

bring-mcp

This project implements a local Model Context Protocol (MCP) server in TypeScript that exposes the functionalities of the Bring! shopping list API. It enables applications like Claude Desktop to interact with your Bring! shopping lists using standardized MCP tools.

The server integrates the bring-shopping npm package for Bring! API access and leverages @modelcontextprotocol/sdk to provide an MCP-compliant server interface.

Disclaimer:
This is a personal project. I am not affiliated with Bring! Labs AG in any way.
This project uses an unofficial Bring! API, which may change or be blocked at any time.
This could cause the MCP server to stop functioning without prior notice.


🧩 Recommended Claude Desktop Configuration

To use this server in Claude Desktop via npx, insert the following into your claude_desktop_config.json file:

{
  "mcpServers": {
    "bring-mcp": {
      "command": "npx",
      "args": ["-y", "bring-mcp@latest"],
      "env": {
        "MAIL": "your_bring_email@example.com",
        "PW": "YOUR_BRING_PASSWORD_HERE"
      }
    }
  }
}

This is the recommended and most portable configuration. It ensures you always use the latest version published to npm without needing local installation.


🚀 Features

  • Automatic Authentication: No manual login required - authentication happens automatically on first API call
  • Exposes Bring! API functions as MCP tools:
    • 🧾 Load shopping lists
    • 🛒 Get and modify items (add, remove, move)
    • 📦 Batch operations (save multiple items, delete multiple items)
    • 🖼 Save/remove item images
    • 👥 Manage list users
    • 🎯 Get default shopping list UUID
    • 🌐 Load translations & catalog
    • 📨 Retrieve pending invitations
  • Communicates via STDIO (for use with Claude Desktop or MCP Inspector)
  • Supports Bring! credentials via .env file or injected environment variables

Available Tools

  • loadLists: Load all shopping lists from Bring!
  • getItems: Get all items from a specific shopping list
  • getItemsDetails: Get details for items in a list
  • saveItem: Save an item to a shopping list with optional specification
  • saveItemBatch: Save multiple items to a shopping list in one operation
  • removeItem: Remove an item from a specific shopping list
  • moveToRecentList: Move an item to the recently used items list
  • deleteMultipleItemsFromList: Delete multiple items from a list by their names
  • saveItemImage: Save an image for an item on a shopping list
  • removeItemImage: Remove an image from an item
  • getAllUsersFromList: Get all users associated with a shopping list
  • getUserSettings: Get settings for the authenticated user
  • getDefaultList: Get the UUID of the default shopping list (use when user doesn't specify a list)
  • loadTranslations: Load translations for the Bring! interface
  • loadCatalog: Load the Bring! item catalog
  • getPendingInvitations: Get pending invitations to join shopping lists

⚙️ Setup and Installation

  1. Clone the repo (or obtain the files)

  2. Navigate into the project directory:

    cd path/to/bring-mcp
    
  3. Install dependencies:

    npm install
    
  4. Create .env file (if not injecting ENV directly):

    MAIL=your_email@example.com
    PW=your_password
    
  5. Build the project:

    npm run build
    
  6. Make script executable (optional on Unix):

    chmod +x build/src/index.js
    

🏃 Running the Server

Launch the MCP server with:

node build/src/index.js

If successful, you'll see: MCP server for Bring! API is running on STDIO (on stderr).


🧪 Testing with MCP Inspector

  1. Ensure npm run build has been executed.

  2. Ensure .env with valid credentials exists.

  3. Run Inspector:

    npx @modelcontextprotocol/inspector node /ABS/PATH/bring-mcp/build/src/index.js
    

🧩 Claude Desktop Integration (Manual Local Setup)

Alternatively, if you prefer a locally built and installed version:

{
  "mcpServers": {
    "mcp-bring": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/TO/bring-mcp/build/src/index.js"],
      "env": {
        "MAIL": "your_bring_email@example.com",
        "PW": "YOUR_BRING_PASSWORD_HERE"
      }
    }
  }
}

🔧 Development

Testing

Run tests with:

npm run test

This command runs formatting, linting, and Jest tests with coverage reporting.

For CI testing:

npm run test:ci

Building

Build the project:

npm run build

Key Dependencies

  • @modelcontextprotocol/sdk: For MCP server implementation
  • @modelcontextprotocol/inspector: For testing and debugging MCP servers
  • bring-shopping: Node.js wrapper for the Bring! API
  • zod: For schema definition and validation
  • dotenv: For managing environment variables

✅ Final Notes

  • 🔒 Avoid committing your .env file.
  • 🧼 Keep credentials out of version control.
  • 🛠 MCP Inspector is invaluable for debugging.
  • 🔄 Authentication is handled automatically - no manual login required.
  • 📦 Use batch operations for efficiency when working with multiple items.

Happy coding with MCP and Bring! 🎉

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