HelloFresh MCP Server
Enables AI assistants to manage HelloFresh meal kit accounts by browsing menus, selecting recipes, and modifying delivery schedules. It supports updating dietary preferences, managing subscriptions, and rating past orders through Playwright-based browser automation.
README
@striderlabs/mcp-hellofresh
A Model Context Protocol (MCP) connector for HelloFresh meal kit delivery. Enables AI assistants like Claude to manage your HelloFresh account — browse menus, select meals, manage deliveries, update preferences, and more.
Features
| Tool | Description |
|---|---|
get_menu |
Browse current week's recipes with filters |
get_recipe_details |
Full recipe info: ingredients, instructions, nutrition |
select_meals |
Choose meals for an upcoming delivery |
skip_week |
Skip a delivery week |
get_delivery_schedule |
View all upcoming deliveries |
modify_delivery |
Change a delivery date |
get_preferences |
View dietary preferences and allergens |
update_preferences |
Update dietary/cuisine preferences |
get_subscription |
View current plan (servings, frequency, price) |
modify_subscription |
Change plan size or delivery frequency |
get_past_orders |
Browse order history |
rate_recipe |
Rate a recipe after cooking |
Requirements
- Node.js 18+
- A HelloFresh account
- Playwright browser (auto-installed)
Installation
npm install @striderlabs/mcp-hellofresh
npx playwright install chromium
Configuration
Set your HelloFresh credentials as environment variables:
export HELLOFRESH_EMAIL="your@email.com"
export HELLOFRESH_PASSWORD="yourpassword"
Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"hellofresh": {
"command": "npx",
"args": ["-y", "@striderlabs/mcp-hellofresh"],
"env": {
"HELLOFRESH_EMAIL": "your@email.com",
"HELLOFRESH_PASSWORD": "yourpassword"
}
}
}
}
Config file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Usage with Claude Code
claude mcp add hellofresh -- npx -y @striderlabs/mcp-hellofresh
Then set env vars or add them to the MCP config.
Example Prompts
Once connected, you can ask Claude:
- "What meals are available this week on HelloFresh?"
- "Show me the recipe details and nutrition for the teriyaki salmon"
- "Select the chicken tacos and mushroom pasta for next week's delivery"
- "Skip my HelloFresh delivery for week 2024-W05"
- "Change my delivery date to Friday January 12th"
- "Update my preferences to vegetarian and avoid nuts"
- "How many meals per week am I subscribed to? Can you change it to 3?"
- "Show me my last 5 HelloFresh orders"
- "I just made the lemon herb chicken — rate it 4 stars"
Tool Reference
get_menu
week_offset (optional, 0-4): Week offset from current week
get_recipe_details
recipe_id (required): The recipe identifier from get_menu
select_meals
week_id (required): Week identifier, e.g. "2024-W01"
meals (required): Array of { recipe_id, servings? } objects
skip_week
week_id (required): Week identifier to skip
get_delivery_schedule
No parameters required.
modify_delivery
week_id (required): Week identifier
new_date (required): New date in YYYY-MM-DD format
get_preferences
No parameters required.
update_preferences
vegetarian (optional): boolean
family_friendly (optional): boolean
dietary_preferences (optional): string[]
allergens (optional): string[]
cuisine_preferences (optional): string[]
get_subscription
No parameters required.
modify_subscription
meals_per_week (optional, 2-5): Number of meals
servings_per_meal (optional, 2-4): Number of servings
frequency (optional): "weekly" | "biweekly"
get_past_orders
limit (optional, 1-50): Max orders to return (default: 10)
rate_recipe
recipe_id (required): Recipe to rate
rating (required, 1-5): Star rating
comment (optional): Written review up to 500 chars
How It Works
This connector uses Playwright browser automation to interact with the HelloFresh website on your behalf. It launches a headless Chromium browser, logs in with your credentials, and navigates the site to perform the requested actions.
Note: This connector interacts with the HelloFresh website through browser automation. Website changes may affect functionality. Use responsibly and in accordance with HelloFresh's terms of service.
Security
- Credentials are passed via environment variables only — never hardcoded
- The browser runs in headless mode with no persistent storage
- Sessions are not saved between server restarts
License
MIT
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。