Mealie MCP Server
Enables AI assistants to interact with Mealie for recipe management, meal planning, and shopping list operations. Supports searching and managing recipes, creating meal plans, and generating shopping lists from recipes or meal plans.
README
Mealie MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Mealie for recipe management, meal planning, and shopping lists.
Features
Tools (28 total)
Recipes
mealie_recipes_search- Search recipes by name, tags, or categoriesmealie_recipes_get- Get full recipe details including ingredients and instructionsmealie_recipes_list- List all recipes with paginationmealie_recipes_create- Create a new recipemealie_recipes_create_from_url- Import recipe by scraping a URLmealie_recipes_update- Update an existing recipemealie_recipes_delete- Delete a recipe
Meal Planning
mealie_mealplans_list- List meal plans for a date rangemealie_mealplans_today- Get today's mealsmealie_mealplans_get- Get specific meal plan entrymealie_mealplans_get_date- Get meals for a specific datemealie_mealplans_create- Create meal plan entrymealie_mealplans_update- Update meal plan entrymealie_mealplans_delete- Delete meal plan entrymealie_mealplans_random- Get random meal suggestion
Shopping Lists
mealie_shopping_lists_list- List all shopping listsmealie_shopping_lists_get- Get shopping list with itemsmealie_shopping_lists_create- Create new shopping listmealie_shopping_lists_delete- Delete shopping listmealie_shopping_items_add- Add item to listmealie_shopping_items_add_bulk- Add multiple items at oncemealie_shopping_items_check- Mark item checked/uncheckedmealie_shopping_items_delete- Remove item from listmealie_shopping_add_recipe- Add recipe ingredients to listmealie_shopping_generate_from_mealplan- Generate shopping list from meal planmealie_shopping_clear_checked- Clear all checked items
Resources
recipes://list- Browse all recipesrecipes://{slug}- View specific recipemealplans://current- Current week's meal planmealplans://today- Today's mealsmealplans://{date}- Specific date's mealsshopping://lists- All shopping listsshopping://{list_id}- Specific shopping list
Prerequisites
- Docker (or Podman)
- A running Mealie instance
- Mealie API token
Quick Start
1. Get the Docker Image
Option A: Pull from GitHub Container Registry (recommended)
docker pull ghcr.io/mdlopresti/mealie-mcp:latest
Option B: Build from source
git clone https://github.com/mdlopresti/mealie-mcp.git
cd mealie-mcp
docker build -t mealie-mcp:latest .
2. Get Your API Token
- Log into your Mealie instance
- Go to User Settings (click your name in sidebar)
- Navigate to API Tokens
- Create a new token (e.g., "MCP Server")
- Copy the token immediately (it won't be shown again)
3. Configure Claude Code
Add to .mcp.json in your project root:
{
"mcpServers": {
"mealie": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "MEALIE_URL=https://your-mealie-instance.com",
"-e", "MEALIE_API_TOKEN=your-api-token-here",
"ghcr.io/mdlopresti/mealie-mcp:latest"
]
}
}
}
Then add mealie to your ~/.claude/settings.json:
{
"allowedMcpServers": [
{ "serverName": "mealie" }
]
}
4. Test the Connection
Restart Claude Code and try:
Can you search for recipes in Mealie?
Development
Local Development (without Docker)
# Create virtual environment
python -m venv venv
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt
# Set environment variables
export MEALIE_URL=https://your-mealie-instance.com
export MEALIE_API_TOKEN=your-api-token
# Run server
python -m src.server
Project Structure
mealie-mcp/
├── Dockerfile # Container definition
├── requirements.txt # Python dependencies
├── build.sh # Build helper script
└── src/
├── server.py # MCP server entry point
├── client.py # Mealie API client
├── tools/ # MCP tool implementations
│ ├── recipes.py
│ ├── mealplans.py
│ └── shopping.py
└── resources/ # MCP resource implementations
├── recipes.py
├── mealplans.py
└── shopping.py
Security
- Never commit API tokens - Use environment variables
- The API token has full access to your Mealie account
- Consider creating a dedicated Mealie user for the MCP server
Requirements
- Python 3.12+
- Mealie v1.0+ (tested with v3.6.1)
License
MIT
Contributing
Contributions welcome! Please open an issue or PR.
Related
- Mealie - Self-hosted recipe manager
- Model Context Protocol - MCP specification
- FastMCP - Python MCP framework
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。