Kitchen MCP

Kitchen MCP

Your digital kitchen, powered by AI. Track what you have, discover what you can cook, and get guided through every recipe β€” step by step, timer by timer.

Category
Visit Server

README

🍳 Kitchen MCP

Your digital kitchen, powered by AI. Track what you have, discover what you can cook, and get guided through every recipe β€” step by step, timer by timer.

Whether you're a home cook managing a busy kitchen or a developer building AI-powered cooking assistants, Kitchen MCP gives you the structured foundation to make it real.


πŸ” What is this?

Kitchen MCP is a local-first Model Context Protocol server that connects an AI assistant to your kitchen. It knows your inventory, your recipes, your equipment, your restrictions, and your preferences β€” and it helps you cook better with all of it.

The AI never guesses. The server is always the source of truth.


✨ Features

Feature Status Description
πŸ“¦ Inventory Management βœ… Track food by lot, location, expiry, and state (sealed, opened, cooked, frozen)
πŸ“– Recipe Engine βœ… Create, version, scale, and validate recipes with ingredients, steps, and equipment
🎯 Smart Matching βœ… Find the best recipes based on what you have, your restrictions, and your taste
πŸ‘¨β€πŸ³ Cooking Sessions βœ… Start a session, follow guided steps, track ingredient usage, get help when things go wrong
⏱️ Kitchen Timers βœ… Create, pause, resume, and extend timers tied to cooking steps
🚫 Dietary Restrictions βœ… Set allergies, intolerances, religious and ethical restrictions; server blocks unsafe recipes
🌢️ Taste Preferences βœ… Set spice heat, saltiness, sweetness on a 0-10 scale; recipes scored to match
🍞 Equipment Catalog βœ… Register stoves, pressure cookers, mixers, refrigerators; server checks compatibility
βš–οΈ Unit Conversion βœ… Convert between grams, kilograms, milliliters, teaspoons, tablespoons, cups, and more
πŸ›’ Shopping Lists πŸ”œ Generate shopping needs from recipes and current inventory
πŸ“… Meal Planning πŸ”œ Plan meals for the week based on preferences, expiry, and inventory
⏰ Expiry Tracking πŸ”œ Get notified before food goes bad, use expiring items first

πŸš€ Quick Start

πŸ“‹ Prerequisites

  • Node.js >= 20
  • npm

⬇️ Install

git clone https://github.com/craftpip/kitchen-mcp.git
cd kitchen-mcp
npm install

▢️ Run (stdio)

npm start

🌐 Run (HTTP)

npm run dev -- --http

Server listens on http://0.0.0.0:3100/mcp.

🐳 Docker

docker compose build && docker compose up -d

Data persists in the kitchen-mcp_kitchen-data volume.


πŸ€– Usage with AI Assistants

Add to your MCP client (like OpenCode, Claude Desktop, etc.):

{
  "mcp": {
    "kitchen": {
      "type": "remote",
      "url": "http://localhost:3100/mcp"
    }
  }
}

Once connected, the AI can:

Ask What happens
πŸ—„οΈ "What do I have?" Checks inventory, shows what's in stock
🍽️ "What can I cook for lunch?" Matches recipes to your inventory and preferences
πŸ‘¨β€πŸ³ "Start cooking the egg curry" Creates session, guides through each step
⏱️ "Set a 10-minute timer" Creates kitchen timer, tracks it
πŸ“¦ "Add 1kg of rice to the pantry" Adds inventory lot with full tracking
🚫 "I'm allergic to peanuts" Blocks all peanut-containing recipes

πŸ› οΈ 66 Tools

Category πŸ”§ What it does
πŸ’š System 2 Health check, capabilities
πŸ—ΊοΈ Locations 3 Rooms, shelves, cabinets, drawers
πŸ₯• Ingredients 4 Catalog, aliases, search
πŸ“¦ Inventory 7 Lots, transactions, expiry tracking
🍞 Equipment 6 Appliances, calibration, availability
βš–οΈ Measurements 3 Unit conversion, household containers
πŸ“– Recipes 9 CRUD, versioning, scaling, availability
🚫 Restrictions 3 Allergies, intolerances, dietary rules
🌢️ Preferences 3 Spice heat, saltiness, sweetness
🎯 Matching 1 Recipe scoring engine
πŸ‘¨β€πŸ³ Sessions 16 Cooking lifecycle, step tracking
⏱️ Timers 9 Kitchen timers with full control

πŸ—οΈ Architecture

Kitchen MCP follows a strict principle: the server is the authority.

  • πŸ—„οΈ SQLite with WAL mode for reliability
  • πŸ”’ All state changes go through structured tools
  • πŸ“– Recipe versions are immutable once used in sessions
  • πŸ“¦ Inventory deductions happen via transactions, never direct overwrites
  • πŸ“ Every action is audit-logged

The AI interprets natural language, picks the right tools, and explains results. The server stores facts, validates requests, and enforces rules. Neither side does the other's job.


πŸ§‘β€πŸ’» Development

# Typecheck
npx tsc --noEmit

# Build
npm run build

# Test
npm test

# Dev (HTTP mode)
npm run dev -- --http

πŸ“ Project Structure

src/
β”œβ”€β”€ πŸ› οΈ server/tools/      # 13 tool files, 66 tools
β”œβ”€β”€ πŸ—οΈ domain/            # Services and types per domain
β”œβ”€β”€ βš™οΈ infrastructure/    # Database, audit, idempotency, logging
└── πŸ“¦ shared/            # Response envelope, errors, IDs, time

πŸ“„ License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured