mcp-veggie
Enables tracking of weekly vegetable box deliveries, translating Danish produce names, providing USDA-sourced freshness data, generating zero-waste recipes, and alerting on expiring items.
README
mcp-veggie
MCP server for tracking weekly Aarstiderne veggie box deliveries. Translates Danish produce names, provides USDA-sourced freshness windows, generates zero-waste recipes via local LLM, and alerts when items are about to expire.
Built for a family of 3 in Denmark. Deployed on a K3s cluster alongside an Ollama instance.
Tools
| Tool | Description |
|---|---|
get_current_box |
Fetch this week's box contents with translations, freshness data, and eating order |
generate_recipes |
Zero-waste recipes using current box items, with kid-friendly strategies |
get_meal_plan |
7-day structured plan scheduling perishable items first |
check_alerts |
Items nearing expiration that need attention |
analyze_waste_risk |
Items at risk of going to waste |
mark_item_used |
Mark an item as consumed |
get_eating_order |
Priority list by perishability |
get_freshness_status |
Full freshness report with storage tips |
override_freshness |
Correct a freshness estimate from experience |
set_box_url |
Configure the Aarstiderne box URL |
Setup
cp .env.example .env
# Edit .env with your Ollama host and box URL
npm install
npm run build
npm start
Requires:
- Node.js 20+
- Ollama running with
qwen3.6:27b(or any model viaLLM_MODELenv var) - An Aarstiderne box subscription URL
Configuration
| Variable | Default | Description |
|---|---|---|
PORT |
3006 | HTTP server port |
DB_PATH |
./data/veggie.db | SQLite database path |
LLM_BASE_URL |
http://localhost:11434 | Ollama API base URL |
LLM_MODEL |
qwen3.6:27b | Model for translations/recipes |
LLM_TIMEOUT |
120000 | LLM request timeout (ms) |
Architecture
- Transport: Streamable HTTP (MCP SDK 1.29.0) -- stateless per-request
- Database: SQLite with WAL mode, Drizzle ORM
- LLM: Ollama native API with
think: falsefor fast structured output - Provider: Aarstiderne BOM API (no auth required)
- Translation: Seed cache of 93 Danish produce names + LLM fallback
- Freshness: 70-item USDA dataset + LLM fallback with conservative bias
K8s Deployment
kubectl apply -f k8s/
The deployment expects:
- A PVC named
mcp-veggie-datafor the SQLite file - Ollama accessible at the
LLM_BASE_URLin the configmap ghcr-credsimagePullSecret for the container image
Connecting via Hermes
Register the MCP server endpoint in your Hermes gateway configuration:
servers:
- name: mcp-veggie
url: http://mcp-veggie.mcp-veggie.svc.cluster.local:3006/mcp
transport: streamable-http
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。