RestaurantDoctorAI

Official registry Maps, travel and weather

Free restaurant profit check, recipe costing, calculators, website check, deadlines, guides, blog.

What can you do with RestaurantDoctorAI?

  • restaurantdoctor_get_questions: the 12 questions and the answer values each accepts, worded for the restaurant's country.
  • restaurantdoctor_run_free_check: scores the 12 answers against RestaurantDoctorAI's targets for the type of restaurant: the grade, grades by area, the estimated profit leak a month and a year, the biggest leak and the first fix, with a link to the same re...
  • restaurantdoctor_cost_recipe: costs a recipe's ingredient lines as a draft in US dollars, weighed with USDA data and priced with the owner's prices or dated US public prices, with a link to check it on the website.
  • restaurantdoctor_prime_cost: food, drink and labor as a share of sales, against the target for the type of restaurant.
  • restaurantdoctor_labor_cost: labor as a share of sales, the hours a sales forecast can pay for, or the sales per labor hour line.
  • restaurantdoctor_break_even: the sales a month, week and day needed to pay every bill.
  • restaurantdoctor_restaurant_budget: a month's expected sales split by RestaurantDoctorAI's targets, with what's left and break-even.
  • restaurantdoctor_plate_cost: one plate's cost from pack prices, and the menu price for a target food cost.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code
claude mcp add --transport http restaurantdoctorai 'https://restaurantdoctorai.com/api/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "restaurantdoctorai": {
            "type": "http",
            "url": "https://restaurantdoctorai.com/api/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. RestaurantDoctorAI MCP server
  2. Configure it
  3. Use it
  4. Tools (21, all read-only)
  5. Privacy
  6. Contact

RestaurantDoctorAI MCP server

A free, read-only remote MCP server for independent restaurant owners. It runs RestaurantDoctorAI's 12-question profit check, costs recipes, works out the website's free restaurant calculators from the owner's own figures, checks a restaurant's website, lists US tax and permit deadlines, and searches a sourced library of guides. Every answer links back to the same page on restaurantdoctorai.com, where the owner can check it.

This repository holds the server's description only. The server itself runs on restaurantdoctorai.com; its source is not public.

Configure it

VS Code (GitHub Copilot)

Add it to .vscode/mcp.json, or run MCP: Add Server and paste the address:

{
  "servers": {
    "restaurantdoctorai": {
      "type": "http",
      "url": "https://restaurantdoctorai.com/api/mcp"
    }
  }
}
Claude

In Claude on the web or the desktop app: Customize › Connectors › + › Add custom connector, name it RestaurantDoctorAI, paste https://restaurantdoctorai.com/api/mcp, and choose no sign-in.

Any other MCP client

Add a remote server with the address above, transport Streamable HTTP, and no authentication.

Use it

Ask in plain words, for example:

  • "Run the RestaurantDoctorAI free profit check for my restaurant."
  • "Last week we sold 24,000, bought 7,400 of food and drink and paid 6,900 in wages. What's my prime cost?"
  • "Our burger is 14 dollars in the restaurant and the delivery app takes 30%. What should it cost on the app?"
  • "Cost this recipe. It makes 8 plates, and I pay 28 dollars for 5 lb of ground beef."
  • "What tax and permit deadlines does my Texas restaurant have coming up?"

Tools (21, all read-only)

Profit check

  • restaurantdoctor_get_questions: the 12 questions and the answer values each accepts, worded for the restaurant's country.
  • restaurantdoctor_run_free_check: scores the 12 answers against RestaurantDoctorAI's targets for the type of restaurant: the grade, grades by area, the estimated profit leak a month and a year, the biggest leak and the first fix, with a link to the same result on the website.

Recipe costing

  • restaurantdoctor_cost_recipe: costs a recipe's ingredient lines as a draft in US dollars, weighed with USDA data and priced with the owner's prices or dated US public prices, with a link to check it on the website.

Calculators (the website's free calculators, from the owner's own figures, in any currency unless noted)

  • restaurantdoctor_prime_cost: food, drink and labor as a share of sales, against the target for the type of restaurant.
  • restaurantdoctor_labor_cost: labor as a share of sales, the hours a sales forecast can pay for, or the sales per labor hour line.
  • restaurantdoctor_break_even: the sales a month, week and day needed to pay every bill.
  • restaurantdoctor_restaurant_budget: a month's expected sales split by RestaurantDoctorAI's targets, with what's left and break-even.
  • restaurantdoctor_plate_cost: one plate's cost from pack prices, and the menu price for a target food cost.
  • restaurantdoctor_delivery_price: a dish's break-even price on a delivery app.
  • restaurantdoctor_menu_calories: a dish's calories, rounded the way US, Ontario, or UK and EU menus show them.
  • restaurantdoctor_fica_tip_credit: an estimate of a US restaurant's FICA tip credit (IRS Form 8846), in US dollars.
  • restaurantdoctor_card_fees: a US restaurant's card fees per 100 dollars of card sales, against a dated fair range.
  • restaurantdoctor_booking_fees: what a US restaurant's booking app costs a month, a year and per guest booked.

Printable sheets (the same math as the website's free sheets)

  • restaurantdoctor_cash_out: one drawer's nightly cash close.
  • restaurantdoctor_tip_out: a server's tip-out, or a tip pool shared by hours and points.
  • restaurantdoctor_par_levels: par levels and what to order for up to 50 items.

Website and deadlines

  • restaurantdoctor_check_website: checks a restaurant's own website (secure, made for phones, a readable menu, online ordering, Google's phone speed test) and says what to fix first.
  • restaurantdoctor_deadlines: a US restaurant's coming federal and state tax, payroll, license and permit dates, each with its rule and official source.

Sourced library

  • restaurantdoctor_search_knowledge: searches RestaurantDoctorAI's guides, blog posts, step-by-step fixes, targets, sourced facts and how-tos, returning passages with their links and sources.
  • restaurantdoctor_list_knowledge: lists the library's entries by kind.
  • restaurantdoctor_read_knowledge: reads one entry in full, in parts for a long one.

Privacy

Nothing sent to the server is stored: not the answers, recipes, figures, website addresses or search words. Only anonymous daily counts are kept (how many checks, drafts, calculator runs, website checks, calendars, searches and reads). Details: https://restaurantdoctorai.com/privacy

Results are estimates and reminders, not financial, tax or legal advice.

Contact

  • Support: support@restaurantdoctorai.com
  • Security: security@restaurantdoctorai.com
  • Published by Gomorra Labs LLC

Frequently asked questions

What is RestaurantDoctorAI?

Free restaurant profit check, recipe costing, calculators, website check, deadlines, guides, blog.

How do I install RestaurantDoctorAI?

It runs as a remote server. In Claude Code: claude mcp add --transport http restaurantdoctorai 'https://restaurantdoctorai.com/api/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does RestaurantDoctorAI need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is RestaurantDoctorAI open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains RestaurantDoctorAI?

It is published by FelixNovaNexus. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.