graziechef-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
graziechef-mcp (@deusflight/graziechef-mcp on npm)
Restaurant math for your AI assistant. This is an MCP server for chefs, restaurant owners and consultants: food cost, menu price with VAT, recipe scaling and the EU 14 allergens matrix, using the same formulas as the free tools on graziechef.com/tools.
The calculations run locally. There is no API key, no account and no network call.
Install
Claude Desktop
Add this to claude_desktop_config.json (Settings > Developer > Edit Config):
{
"mcpServers": {
"graziechef": {
"command": "npx",
"args": ["-y", "@deusflight/graziechef-mcp"]
}
}
}Cursor
Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:
{
"mcpServers": {
"graziechef": {
"command": "npx",
"args": ["-y", "@deusflight/graziechef-mcp"]
}
}
}Claude Code
claude mcp add graziechef -- npx -y @deusflight/graziechef-mcpRequires Node.js 18 or newer.
Related MCP server: Gamito
Tools
Tool | What it answers |
| Cost of a dish from its ingredients, the price that hits your target food cost %, and your actual food cost % at the current price. |
| From plate cost and target food cost: net price, price including VAT, menu price rounded up to a clean step, gross profit and real food cost after rounding. |
| Scale a recipe from N to M portions. Returns every scaled quantity, plus batch cost and cost per portion when unit costs are given. |
| The dish x allergen table required in the EU (Reg. 1169/2011, Annex II), with the dishes to avoid for each allergen. Accepts English, Italian or common names ("shrimp", "dairy"). |
currency is an optional ISO code (default EUR) and only affects formatting.
Ask your assistant things like:
"My carbonara uses 0.12 kg guanciale at €18/kg, 0.1 kg pasta at €2/kg and 2 eggs at €0.30. What should it cost on the menu at 28% food cost with 10% VAT?"
"Scale this tiramisu from 6 to 40 portions."
"Build the allergen matrix for my menu."
Example output (menu_price_calculator, plate cost 3.20, 30% target, 10% VAT, round to 0.50):
Net price (before tax): €10.67
Price incl. 10% tax: €11.74
Menu price (rounded up to 0.5): €12.00
Gross profit per plate (net of tax): €7.71
Real food cost after rounding: 29.3%Each result ends with a link to the matching interactive tool on graziechef.com.
Notes
The allergen tool does not guess allergens from dish names. You declare them, and it builds the table. Always check recipes and supplier labels.
Run the tests with
npm test. They start the server over stdio and call every tool.
Development (inside the GrazieChef monorepo)
The package is self-contained (own package.json and lockfile, plain .mjs with no build). Run
npm ci && npm test here, then rm -rf node_modules: the root vitest config only excludes the root
node_modules, so a local install here would make the root gate pick up zod's own test files.
Publish: npm publish --access public, then mcp-publisher publish for server.json.
License
MIT. Made by GrazieChef, digital menus and kitchen tools for restaurants.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Read-only kitchen costing, recipe scaling, UK GP, starter menus, and prep lists for chefs.
Read-only UK kitchen costing: cost recipes, set menu prices, work out GP with VAT, build prep lists.
The brain for restaurant costs, pricing, and true profit (read/edit menu, recipes, costs).
AI copilot for artisan food makers — stock, orders, HACCP and billing from your chat.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides hospitality intelligence tools for restaurant optimization, including menu profitability analysis, food cost calculation, reservation management, review sentiment analysis, and allergen checking.8 npm34 PyPIMIT
- FlicenseBqualityDmaintenanceEnables AI agents to generate budget-disciplined, allergy-safe weekly meal plans, shopping lists, and meal swaps using a fully local deterministic engine.20-
- FlicenseNot gradedqualityBmaintenanceEnables AI assistants to search recipes, compose nutritionally balanced meals, optimize weekly meal plans based on macro targets for family members, and generate consolidated grocery lists from a personal recipe database.-
- AlicenseAqualityDmaintenanceEnables interactive recipe costing and menu-item pricing with deterministic math, including waste and margin calculations, and distinguishes whether figures came from the calculator or the model.2MIT