MMCPMarkets
WH

worryzyy/howtocook-mcp

Developer tools

This page was translated automatically. Technical details may differ from the original. View the original

795 stars 61 forks Quality 69 Trend 28
Repository Install

MCP server based on Anduin2017 / HowToCook (Programmer's Guide to Cooking at Home).

Overview

The MCP (Model Context Protocol) server built on Anduin2017/HowToCook allows AI assistants to recommend recipes and plan meals, solving the century-old challenge of "what to eat today!" Data source: Anduin2017/HowToCook ⭐ If you don't have a star, go and get a star! As follows: Please make sure you have installed the latest version of Claude Desktop. The current MCP DXT file has been uploaded to the codebase, which can be downloaded or forked to build it yourself 2. In the folder containing the local MCP server, run dxt init. This is the root directory of your MCP. This command will guide you to create manifest.json Now, any DXT-supported application can run your local MCP server. For example, opening the file with Claude for macOS and Windows will display the installation dialog - 🤖 Claude Desktop Application - 📝 Cursor - 💼 Other clients that support MCP 1. - Get all available recipe data and a cooking encyclopedia -- Use this with caution—the context is too broad 2. - Filter recipes by category, want seafood? Breakfast? Meat? Staple foods? One-click done! 3. - Search for full details of specific recipes by dish name, including ingredients, steps, etc. 4. - Plan delicious dishes for a whole week based on your dietary restrictions, allergens, and number of diners 5. - A blessing for choice paralysis! Recommend today's menu directly based on the number of people, no more agonizing - --transport - Select transmission mode (default is stdio) - --port - listen port for HTTP or SSE transmission (default is 3000)

Overview (machine translated)

English | Chinese Simplified

The CDN acceleration and security protection for this project are sponsored by Tencent EdgeOne

Asia’s Best CDN, Edge and Security Solutions - Tencent EdgeOne

Transform your AI assistant into a personal chef, offering advice for your daily meals!

The MCP (Model Context Protocol) server built on Anduin2017/HowToCook allows AI assistants to recommend recipes and plan meals, solving the century-old challenge of “what to eat today!”

Data source: Anduin2017/HowToCook ⭐ If you don’t have a star, go and get a star!

🎉 Want to use your current MCP directly? Try it now https://howtocookmcp.weilei.site/

🎉 At the same time, we also offer DXT (Desktop Extensions) for everyone to experience, allowing one-click installation to Claude Desktop

As follows: Please make sure you have installed the latest version of Claude Desktop. The current MCP DXT file has been uploaded to the codebase, which can be downloaded or forked to build it yourself

How can local development be packaged into DXT?

  1. Run npm install -g @anthropic-ai/dxt

  2. In the folder containing the local MCP server, run dxt init. This is the root directory of your MCP. This command will guide you to create manifest.json

  3. Run dxt pack to create a dxt file

Now, any DXT-supported application can run your local MCP server. For example, opening the file with Claude for macOS and Windows will display the installation dialog

For details, see: anthropics/dxt

📸 Effect Preview

🔌 Supported MCP clients

This server is suitable for all AI assistants and clients that support the MCP protocol, including but not limited to:

  • 🤖 Claude desktop application
  • 📝 Cursor
  • 💼 Other clients that support MCP

✨ Delicious Features

This MCP server offers the following gourmet tools:

  1. ** Query 📚 all recipes** - Get all available recipe data, cooking encyclopedia – use this with caution – the context is too large
  2. 🔍 Search recipes by category - Filter recipes by category, want seafood? Breakfast? Meat? Staple foods? One-click done!
  3. ** 📖 Query Specified Recipes** - Query the complete details of a specific dish by name, including ingredients, steps, and more
  4. 🧩 Smart Meal Recommendations – Plan delicious meals for you throughout the week based on your dietary restrictions, allergens, and number of diners
  5. 🎲 Don’t Know What to Eat - A blessing for those struggling to choose! Directly recommend today’s menu based on the number of people, so no more agonizing

🚀 Get started quickly

📋 Prerequisites

  • Node.js 16.0.0+ 🟢

This page was translated automatically. Technical details may differ from the original.

Install

npx -y howtocook-mcp
New to MCP? Start with the mcpskill.org guide →

Configuration

{ "mcpServers": { "howtocook-mcp": { "command": "npx", "args": ["-y", "howtocook-mcp"] } } }