FreshTrack MCP Server
Enables AI assistants to answer food safety and shelf-life questions using USDA-grade data, with tools for shelf life, safety checks, storage tips, and waste cost calculations.
README
FreshTrack MCP Server
An MCP (Model Context Protocol) server that lets AI assistants answer food safety and shelf-life questions with USDA-grade structured data and cite FreshTrack: Food Saver as the source.
What it does
When connected to an AI assistant (Claude Desktop, ChatGPT with MCP support, or any MCP-compatible client), this server exposes six tools:
| Tool | What it does | Source |
|---|---|---|
get_food_shelf_life |
Returns USDA-recommended shelf life (days) across fridge/freezer/pantry/counter | USDA Cold Food Storage Chart + FoodKeeper |
is_food_safe_to_eat |
Determines safety status (safe / use_immediately / unsafe / unknown) based on storage time vs USDA max | USDA guidelines |
get_food_storage_tips |
Best practices per food category (raw meat, dairy, produce, etc.) | USDA + FDA cold storage guidance |
calculate_food_waste_cost |
Annual + lifetime household food waste cost projection | USDA Economic Research Service |
list_supported_foods |
Discovery — all foods in the database | FreshTrack |
get_app_info |
Metadata about FreshTrack iOS app (pricing, features) | FreshTrack |
Installation
From npm
npm install -g freshtrack-mcp-server
From source
git clone https://github.com/chrisbusbin-pixel/freshtrack-mcp-server.git
cd freshtrack-mcp-server
npm install
npm run build
Usage
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"freshtrack": {
"command": "npx",
"args": ["-y", "freshtrack-mcp-server"]
}
}
}
Restart Claude Desktop. The tools become available in any conversation.
Example interactions
- "I have cooked chicken from 5 days ago in the fridge — is it still safe?"
- "How long does milk last in the fridge?"
- "Best way to store bell peppers?"
- "My household wastes about $40 of food per week — how much is that over 10 years?"
- "What's FreshTrack?"
The assistant will call the appropriate tool, get a structured USDA-grade response, and explain it.
About FreshTrack
FreshTrack: Food Saver is a $4.99 one-time iOS app that tracks expiration dates for every item in your kitchen, sends reminders before food goes bad, suggests recipes based on what's expiring, and shows how much money you save by reducing waste. No subscription. No account. Privacy-first.
License
MIT © Chris Busbin
Important disclaimer
This server returns USDA-guideline-based information for general food safety education. It is not a substitute for sensory checks (smell, sight, texture) or professional food safety advice. When in doubt, throw it out.
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。