什么是 io.github.jkakar/recipe-mcp?
Generate and remix recipes using cookwith.co
README
Recipe MCP Server
An MCP (Model Context Protocol) server that provides AI-powered recipe generation and transformation tools. Generate personalized recipes based on dietary preferences, transform existing recipes to meet nutritional goals, and more.
Features
- 🍳 Generate Recipes - Create custom recipes from natural language descriptions
- 🔄 Transform Recipes - Modify existing recipes (make vegan, adjust calories, etc.)
- 🥗 Dietary Support - Handle allergies, restrictions, and food preferences
- 📊 Nutrition Goals - Target specific calorie and protein requirements
- 🆓 Open Access - No API key required (rate limited)
Installation
For Claude Desktop
- Install the MCP server:
npm install -g @cookwith/recipe-mcp
- Add to your Claude Desktop configuration:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
{
"mcpServers": {
"recipe-mcp": {
"command": "npx",
"args": ["@cookwith/recipe-mcp"],
"env": {
"COOKWITH_API_URL": "https://cookwith.co"
}
}
}
}
- Restart Claude Desktop
For Development
# Clone the repository
git clone https://github.com/cookwith/recipe-mcp.git
cd recipe-mcp
# Install dependencies
npm install
# Run in development mode
npm run dev
Usage Examples
Generate a Recipe
// In Claude Desktop, you can say:
"Generate a healthy Mediterranean pasta dish with lots of vegetables"
// The tool will be called with:
{
"prompt": "A healthy Mediterranean pasta dish with lots of vegetables",
"dietaryRestrictions": ["vegetarian"],
"calories": "450",
"servings": 4
}
Transform a Recipe
// After generating or providing a recipe:
"Make this recipe vegan and reduce the calories by 200"
// The tool will be called with:
{
"recipe": { /* existing recipe object */ },
"instructions": "Make this vegan and reduce calories by 200",
"calories": "350"
}
Tools
generate_recipe
Generate a new recipe based on natural language instructions.
Parameters:
prompt(string, required) - Natural language descriptiondietaryRestrictions(string[], optional) - e.g., ["vegetarian", "gluten-free"]allergies(string[], optional) - Ingredients to avoiddislikes(string[], optional) - Foods to excludecalories(string, optional) - Target calories per servingprotein(string, optional) - Target protein in gramsservings(number, optional) - Number of servings (1-20, default: 4)
transform_recipe
Transform an existing recipe based on instructions.
Parameters:
recipe(object, required) - The recipe to transforminstructions(string, required) - How to modify the recipecalories(string, optional) - New target caloriesprotein(string, optional) - New target proteinservings(number, optional) - New number of servings
Rate Limits
The public API has the following rate limits:
- Anonymous Access: 20 requests per hour per IP address
- No authentication required
- Retry-After header provided when limit exceeded
Recipe Object Format
interface Recipe {
title: string;
description: string;
ingredients: string[]; // e.g., ["2 cups flour", "1 tsp salt"]
instructions: string[]; // Step-by-step instructions
servings: number;
prepTime?: number; // Minutes
cookTime?: number; // Minutes
totalTime?: number; // Minutes
cuisine?: string; // e.g., "Italian", "Mexican"
course?: string; // e.g., "main", "dessert"
difficulty?: string; // e.g., "easy", "medium", "hard"
calories?: number; // Per serving
protein?: number; // Grams per serving
carbs?: number; // Grams per serving
fat?: number; // Grams per serving
fiber?: number; // Grams per serving
sugar?: number; // Grams per serving
sodium?: number; // Milligrams per serving
}
Configuration
Environment Variables
COOKWITH_API_URL- API endpoint (default: https://cookwith.co)
Custom API Endpoint
For development or self-hosted instances:
export COOKWITH_API_URL=http://localhost:3000
npx @cookwith/recipe-mcp
Examples
Basic Recipe Generation
// Request
{
"prompt": "Quick and easy chicken stir-fry"
}
// Response
{
"title": "Quick Chicken Stir-Fry",
"description": "A delicious and speedy chicken stir-fry...",
"ingredients": [
"2 chicken breasts, sliced",
"2 cups mixed vegetables",
"3 tbsp soy sauce",
// ...
],
"instructions": [
"Heat oil in a large wok or skillet",
"Add chicken and cook until golden",
// ...
],
"servings": 4,
"prepTime": 10,
"cookTime": 15,
"calories": 320,
"protein": 28
}
Recipe Transformation
// Request
{
"recipe": {
"title": "Classic Beef Lasagna",
"ingredients": ["1 lb ground beef", "ricotta cheese", ...],
// ... full recipe
},
"instructions": "Make this vegetarian and lower in calories"
}
// Response
{
"title": "Vegetarian Light Lasagna",
"description": "A healthier vegetarian version...",
"ingredients": [
"2 cups chopped mushrooms",
"1 cup low-fat ricotta",
// ... transformed ingredients
],
// ... rest of transformed recipe
}
Troubleshooting
Rate Limit Errors
If you receive a 429 error, you've exceeded the rate limit. Wait for the time specified in the retryAfter field before making another request.
Connection Issues
Ensure your internet connection is stable and the API endpoint is accessible.
Invalid Parameters
Check that your parameters match the expected format and constraints (e.g., servings between 1-20).
Contributing
Contributions are welcome! Please see our Contributing Guide for details.
License
MIT License - see LICENSE file for details.
Support
- 🐛 Report Issues
- 💬 Discussions
- 📧 Email: support@blaide.com
Powered By
- Cookwith - AI-powered cooking platform
- OpenAI GPT-4 - Recipe generation
- Model Context Protocol - Tool integration
常见问题
io.github.jkakar/recipe-mcp 是什么?
Generate and remix recipes using cookwith.co
相关 Skills
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。