一个 Model Context Protocol 服务器，它将 Mealie（一个自托管的食谱管理器）公开为一组 LLM 可调用的工具。它允许 Claude Desktop / Claude Code（或任何 MCP 客户端）在您自己的 Mealie 实例上搜索食谱、获取详细信息、管理膳食计划和编辑购物清单。
工具 | 用途 |
| 搜索食谱；返回 slug、名称、描述、标签、类别 |
| 获取指定 slug 的完整食谱 JSON |
| 两个 ISO 日期之间的膳食计划条目 |
| 所有购物清单的 ID 和名称 |
| 向清单添加自由文本项目 |
| 创建一个空白食谱；返回生成的 slug |
| 添加膳食计划条目 |
Related MCP server: Mealie MCP Server
Python 3.11+
一个正在运行的 Mealie 实例（自托管；已针对 Mealie v2 进行测试）
一个长期有效的 Mealie API 令牌（在 Mealie UI 中：用户个人资料 → API 令牌）
将 .env.example 复制到 .env 并填入相应值：
cp .env.example .env变量 | 必需 | 默认 | 描述 |
| 是 | — | Mealie 实例的基础 URL（例如 |
| 是 | — | 来自 Mealie 的长期有效持有者令牌 |
| 否 |
|
|
| 否 |
| SSE 模式的绑定地址 |
| 否 |
| SSE 模式的绑定端口 |
pip install -e .
# stdio mode (for Claude Desktop):
MCP_TRANSPORT=stdio mealie-mcp
# sse/http mode (for docker-compose / remote clients):
MCP_TRANSPORT=sse MCP_PORT=8000 mealie-mcpSSE 端点位于 http://<host>:<port>/sse。
编辑 Claude Desktop 的配置文件（macOS: ~/Library/Application Support/Claude/claude_desktop_config.json）：
{
"mcpServers": {
"mealie": {
"command": "mealie-mcp",
"env": {
"MEALIE_URL": "http://localhost:9011",
"MEALIE_API_TOKEN": "paste-your-token-here",
"MCP_TRANSPORT": "stdio"
}
}
}
}如果 mealie-mcp 不在您的 PATH 中，请将 command 指向完整的二进制文件路径（例如 /Users/you/.venvs/mealie-mcp/bin/mealie-mcp）或通过 Python 调用：
{
"mcpServers": {
"mealie": {
"command": "python",
"args": ["-m", "mealie_mcp"],
"env": {
"MEALIE_URL": "http://localhost:9011",
"MEALIE_API_TOKEN": "paste-your-token-here",
"MCP_TRANSPORT": "stdio"
}
}
}
}编辑配置后重启 Claude Desktop。
包含了一个 Dockerfile。要独立运行：
docker build -t mealie-mcp .
docker run --rm -p 8765:8000 \
-e MEALIE_URL=http://host.docker.internal:9011 \
-e MEALIE_API_TOKEN=your-token \
mealie-mcp要将服务器添加到现有的 Mealie 堆栈中，请参阅 docker-compose.snippet.yml：
services:
mealie-mcp:
build:
context: ./mealie-mcp
depends_on:
- mealie
environment:
MEALIE_URL: "http://mealie:9000"
MEALIE_API_TOKEN: "${MEALIE_API_TOKEN}"
MCP_TRANSPORT: "sse"
MCP_HOST: "0.0.0.0"
MCP_PORT: "8000"
ports:
- "8765:8000"将您的 MCP 客户端指向 http://<docker-host>:8765/sse。
在 SSE 模式下运行服务器时，确认其可访问：
curl -N http://localhost:8000/sse您应该会看到一个 SSE 事件流已打开。对于 stdio 模式，Claude Desktop 会处理握手——没有 HTTP 端点。
mealie-mcp/
├── pyproject.toml
├── Dockerfile
├── docker-compose.snippet.yml
├── .env.example
├── README.md
└── src/mealie_mcp/
├── __init__.py
├── __main__.py # CLI entry point (loads .env, dispatches transport)
├── server.py # FastMCP server + tool definitions
└── client.py # Async httpx wrapper for the Mealie REST APIMIT
This server cannot be deployed
Scraps Kitchen gives any AI agent a persistent, household-aware kitchen memory. Unlike generic chatbot recall, Scraps maintains structured cooking data: what's in your fridge (with freshness tracking), who you cook for (with allergens, dietary restrictions, and preferences), your recipe collection (with cook notes and per-diner ratings), your shopping list, and your kitchen equipment. 27 tools across 6 domains let agents read kitchen context, suggest meals that respect dietary safety, update the pantry after cooking, and build a history of what works for your household. Every interaction makes the data richer. Cooking history, preference signals, kitchen awareness = better suggestions next time. All tools work via oAuth and a free scraps.kitchen account.
Household-aware cooking brain: pantry, meal suggestions, dietary safety, recipes, shopping lists.
Search structured recipes, scale servings, match pantry ingredients, and build shopping lists.
Search, read, and edit your Halite recipe collection and shopping lists.
