Cookwith Mcp

io.github.jkakar由 GitHub 账号 jkakar 发布v1.0.2更新于 Nov 10, 2026

AI-powered recipe generation and transformation tools by Cookwith

已验证STDIO仅桌面位置与生活AI 与机器学习

概览

AI 生成的概览

一个本地 MCP 服务器,借助 Cookwith 的烹饪 AI,让助手生成新食谱,并按饮食需求、过敏原和营养目标改造已有食谱。

可以做什么
  • 根据自然语言描述生成食谱,可指定饮食限制、过敏原、不喜欢的食材、热量与蛋白质目标以及份数。
  • 按自然语言指令改造已有食谱(标题、描述、食材、步骤、份数),例如改为素食或无麸质。
  • 按新的热量、蛋白质或份数目标调整食谱。
适用场景
适合让助手在对话中直接构思菜谱,或把已有食谱改造成符合饮食限制、过敏原、份量和营养目标的版本。
运行要求
作为本地进程在桌面端运行,通过 README 中所述的 npm 包以 npx 启动,隐含需要 Node.js 和网络访问。未声明任何账号、API 密钥、环境变量或请求头。
安装前请注意
食谱请求(包括饮食与过敏信息)会发送到 Cookwith 的外部烹饪 AI 服务,请谨慎对待个人健康信息。生成的食谱为 AI 输出,使用前应核对过敏原与食品安全。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Cookwith Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Cookwith MCP Server

An MCP (Model Context Protocol) server that provides AI-powered recipe generation and transformation tools using Cookwith's advanced culinary AI.

Features

  • Recipe Generation: Create custom recipes from natural language descriptions
  • Recipe Transformation: Modify existing recipes based on dietary needs, serving sizes, or other requirements
  • Dietary Support: Handle allergies, dietary restrictions, and nutritional goals
  • Smart Adaptations: Adjust for calories, protein targets, and serving counts

Installation

Via MCP Registry

bash
npx @modelcontextprotocol/create-server install @cookwith/mcp-server

Via npm

bash
npm install -g @cookwith/mcp-server

For Claude Desktop

Add to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

json
{  "mcpServers": {    "cookwith": {      "command": "npx",      "args": ["@cookwith/mcp-server"]    }  }}

Available Tools

generate_recipe

Generate a new recipe based on natural language instructions.

Parameters:

  • prompt (string, required): Natural language description of the desired recipe
  • dietaryRestrictions (array): Dietary restrictions (e.g., vegetarian, vegan, gluten-free)
  • allergies (array): Ingredients to avoid due to allergies
  • dislikes (array): Foods the user doesn't like
  • calories (string): Target calories per serving
  • protein (string): Target protein in grams per serving
  • servings (number): Number of servings (1-20, default: 4)

Example:

javascript
{  "prompt": "A healthy pasta dish with lots of vegetables",  "dietaryRestrictions": ["vegetarian"],  "calories": "500",  "servings": 2}

transform_recipe

Transform or modify an existing recipe based on instructions.

Parameters:

  • recipe (object, required): The recipe to transform
    • title (string): Recipe title
    • description (string): Recipe description
    • ingredients (array): List of ingredients
    • instructions (array): Cooking instructions
    • servings (number): Number of servings
    • Additional optional fields for nutrition, timing, etc.
  • instructions (string, required): How to transform the recipe
  • calories (string): New target calories per serving
  • protein (string): New target protein per serving
  • servings (number): New number of servings

Example:

javascript
{  "recipe": {    "title": "Classic Spaghetti Carbonara",    "description": "Traditional Italian pasta dish",    "ingredients": ["400g spaghetti", "200g guanciale", "4 eggs", "100g pecorino"],    "instructions": ["Cook pasta", "Fry guanciale", "Mix eggs and cheese", "Combine"],    "servings": 4  },  "instructions": "Make it vegetarian and reduce calories",  "calories": "400"}

Usage Examples

With Claude

Once configured, you can use natural language to interact with the tools:

"Generate a healthy dinner recipe for 2 people with chicken and vegetables, around 500 calories per serving"
"Transform this pasta recipe to be gluten-free and dairy-free"

Programmatic Usage

javascript
import { Client } from '@modelcontextprotocol/sdk';
const client = new Client({  name: 'my-app',  version: '1.0.0'});
await client.connect('npx', ['@cookwith/mcp-server']);
// Generate a recipeconst result = await client.callTool('generate_recipe', {  prompt: 'Quick and healthy breakfast',  calories: '350',  servings: 1});

Development

Building from Source

bash
git clone https://github.com/blaideinc/cookwith-mcpcd cookwith-mcpnpm installnpm run build

Running Locally

bash
npm start

Testing

bash
npm test

API Endpoint

The MCP server can also be accessed via HTTP at:

  • Production: https://cookwith.co/api/mcp
  • Development: http://localhost:3000/api/mcp

License

MIT

Support

About Cookwith

Cookwith is an AI-powered cooking platform that generates personalized recipes based on your preferences, dietary restrictions, and taste profile. Learn more at cookwith.co.

来源:README.md,提交 294d135

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.2最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分