Honcho
Memory that reasons: continual learning for stateful agents. Better context, fewer tokens.
Description from the maker (original English)
Generate and remix recipes using cookwith.co
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"recipe": {
"command": "npx",
"args": [
"-y",
"@cookwith/recipe-mcp"
]
}
}
}Run this in your terminal
claude mcp add recipe -- npx -y @cookwith/recipe-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"recipe": {
"command": "npx",
"args": [
"-y",
"@cookwith/recipe-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"recipe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cookwith/recipe-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 10, 2026
The publisher (jkakar) is not the repo owner (blaideinc); someone else may have listed it
No code changes for over a year, or the repo is archived
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 0 of 2 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed 14 months ago, and the latest version (1.0.4) reached the registry 14 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Honcho, ShipSwift, Pm Claude Skills
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Memory that reasons: continual learning for stateful agents. Better context, fewer tokens.
40+ production-ready SwiftUI recipes for building full-stack iOS apps via MCP.
1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
npm install -g @cookwith/recipe-mcp
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": { "recipe-mcp": { "command": "npx", "args": ["@cookwith/recipe-mcp"], "env": { "COOKWITH_API_URL": "https://cookwith.co" } } } }
# Clone the repository
git clone https://github.com/cookwith/recipe-mcp.git cd recipe-mcp
npm install
npm run dev
// 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 }
// 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" }
generate_recipeGenerate 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_recipeTransform 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 servingsThe public API has the following rate limits:
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 }
COOKWITH_API_URL - API endpoint (default: https://cookwith.co)For development or self-hosted instances:
export COOKWITH_API_URL=http://localhost:3000
npx @cookwith/recipe-mcp
// 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 }
// 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 }
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.
Ensure your internet connection is stable and the API endpoint is accessible.
Check that your parameters match the expected format and constraints (e.g., servings between 1-20).
Contributions are welcome! Please see our Contributing Guide for details.
MIT License - see LICENSE file for details.