Saffron MCP Server
Enables AI assistants to interact with Saffron recipe management functionality, including creating and updating recipes, importing from websites or text, and organizing cookbooks. Provides comprehensive recipe management capabilities through Saffron's API with support for ingredients, instructions, timing, and metadata.
README
<img src="docs/saffron.png" alt="🧄" width="24" height="24" style="vertical-align: middle;"> Saffron MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to Saffron recipe management functionality.
💬 Example: Claude using the Saffron MCP server
<p align="center"> <img src="docs/example.png" alt="MCP server running with Claude" /> </p>
✨ Features
This MCP server enables AI assistants to:
- Recipe Management: Create, read, update recipes with full ingredient and instruction support
- Recipe Import: Import recipes from websites or text using Saffron's built-in parsing
- Cookbook Organization: Browse cookbooks, sections, and organize recipes
- Meal Planning: Create, update, and manage meal plans with menu items and notes
- User Account: Access user information and account details
🛠️ Available Tools
👤 User & Account
me- Get your user information
📚 Cookbook Management
cookbooks- Get your cookbookssections_by_cookbook_id- Get sections by cookbook IDrecipes_by_cookbook_and_section_id- Get recipe summaries by section
🍳 Recipe Operations
get_recipe_by_id- Get full recipe details by IDcreate_recipe- Create a new recipeupdate_recipe- Update an existing recipeimport_recipe_from_website- Import recipe from a URL
📅 Meal Planning
menu_planner- Get all menu items and menu notes for a given date rangecreate_menu_item- Create a new menu item (add a recipe to your meal plan)update_menu_item- Update an existing menu item (change date, scale, or section)delete_menu_item- Delete a menu item from your meal plancreate_menu_note- Create a new menu note (informal recipes, meal planning notes)update_menu_note- Update an existing menu notedelete_menu_note- Delete a menu note
📦 Installation
To use this MCP server, you'll need:
- Node.js (version 14 or higher)
- npm/npx (comes with Node.js)
Clone the repository:
git clone https://github.com/tvh/saffron-mcp.git
cd saffron-mcp
npm install
🤖 Setting up Claude
If you haven't setup MCP before, first read more about how to install Claude Desktop client & configure an MCP server.
To add saffron-mcp to Claude, all you need to do is create another entry in the mcpServers section of your claude_desktop_config.json file:
{
"mcpServers": {
"saffron": {
"key": "saffron",
"command": "npx",
"args": [
"tsx",
"/path/to/saffron-mcp/src/index.ts",
"--email",
"<your email>",
"--password",
"<your password>"
]
}
}
}
Restart Claude and you should see the MCP server tools after clicking on the hammerhead icon:

🔗 Related Work
- Paprika 3 MCP - An MCP server for Paprika 3 recipe management
If you're working on similar MCP servers for cooking or recipe management, feel free to open an issue to have your project listed here!
⚠️ Disclaimer
This project is not affiliated with or endorsed by Saffron. It provides client functionality that interacts with Saffron's publicly accessible API. Users are responsible for complying with Saffron's Terms of Service and applicable laws. Please use responsibly and respect rate limits.
📄 License
MIT License - see LICENSE file for details.
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。