1. Home
  2. Servers
  3. Productivity
  4. HowToCook-MCP Server

Server profile

HowToCook-MCP Server

HowToCook-MCP brings the HowToCook recipe collection to AI assistants. It can retrieve recipes, suggest dishes for a group, and build weekly meal plans around ingredient exclusions and allergies.

View repositoryInstall & configure

Server facts

HowToCook-MCP Server

Project

Author
worryzyy
Repository
github.com/worryzyy/HowToCook-mcp
License
Not specified
Category
Productivity

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
782
Last commit
Data as of

Tags

  • Cooking
  • Meal Planning
  • Recipes
  • Shopping Lists

Overview

HowToCook-MCP Server connects MCP assistants to recipes sourced from Anduin2017's HowToCook project. It is designed for everyday cooking questions, from finding a particular dish to deciding what a household should eat during the week. Users can browse recipes by category or request full details for a named recipe, including its ingredients and preparation steps. Categories cover options such as breakfast, seafood, meat dishes, vegetables, soups, desserts, drinks, and staple foods. A separate recommendation workflow takes the number of diners along with allergies and ingredients to avoid, then produces a weekly meal plan and an approximate shopping list.

For quicker decisions, another tool proposes a suitable combination of dishes based on group size. The documented diner-count range is one through ten. There is also a tool that returns the entire recipe collection, although the README cautions that this can consume substantial assistant context. Local use requires Node.js 16 or newer and npm or yarn. The project documents an npm-package configuration, a source build, and desktop-extension packaging for Claude Desktop. Standard input/output is the default transport, with HTTP and SSE also mentioned as alternatives. Cursor, Claude Desktop, and other MCP clients are supported. The README states an MIT license and provides a hosted demonstration separately from the local server configuration.

Install & configure

Requirements

  • Node.js 16.0.0 or later
  • npm or yarn
  • An MCP-compatible client
Documented launch / install command
npx -y howtocook-mcp

For the Cursor npm configuration, the README instructs users to run npm i -g howtocook-mcp first to avoid client creation failures. Source builds and HTTP/SSE alternatives are also described. No required environment variables are stated.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "HowToCook-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "howtocook-mcp"
      ],
      "env": {}
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "HowToCook-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "howtocook-mcp"
      ],
      "env": {}
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "HowToCook-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "howtocook-mcp"
      ],
      "env": {}
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "HowToCook-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "howtocook-mcp"
      ],
      "env": {}
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "HowToCook-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "howtocook-mcp"
      ],
      "env": {}
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
mcp_howtocook_getAllRecipesReturn the full recipe collection; the README warns of large context usage.
mcp_howtocook_getRecipesByCategoryFind recipes within a selected food category.
mcp_howtocook_recommendMealsSuggest a weekly meal plan and rough shopping list using allergies, exclusions, and diner count.
mcp_howtocook_whatToEatRecommend a dish combination for the specified group size.
mcp_howtocook_getRecipeByIdLook up a recipe by name or identifier, including ingredients and cooking steps.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Find ingredients and preparation steps for a specific dish.
  • Browse recipes within a cooking category.
  • Plan weekly meals around allergies and disliked ingredients.
  • Choose a meal combination for a group of one to ten people.

Strengths

  • Combines recipe lookup with weekly planning and shopping guidance.
  • Recommendations accept allergies, exclusions, and diner count.
  • Supports npm execution and a Claude Desktop extension option.

Limitations

  • Retrieving every recipe can use excessive assistant context.
  • The documented recommendation range is limited to ten diners.

Frequently asked questions

The README identifies Anduin2017/HowToCook as the recipe source.

Yes. The recommendation inputs include allergies, ingredients to avoid, and the number of diners.

The documented peopleCount parameter accepts values from one to ten.

That option exists, but the README cautions that it can create a very large context payload.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

MCP Atlassian

Productivity

MCP Atlassian connects assistants to Jira and Confluence for issue tracking and team documentation. It supports Atlassian Cloud and compatible Server or Data Center installations, with tools for searching, reading, creating, and updating content.

pythonstdio6,008 GitHub stars

n8n MCP Server

Productivity

n8n MCP Server lets AI assistants manage workflows and inspect or control executions in an n8n instance. It supports workflow CRUD, activation controls, API execution, and authenticated webhook triggers.

nodestdio1,631 GitHub stars

MCP Shrimp Task Manager

Productivity

Shrimp organizes AI-assisted development into planned, dependent tasks with persistent progress. It helps coding assistants retain project context, research decisions, and work through implementation and verification.

nodestdio2,146 GitHub stars

ATLAS Task Management System

Productivity

ATLAS lets LLM agents manage linked projects, tasks, and knowledge through MCP. It uses Neo4j for relationships, dependencies, and cross-entity search, with stdio and streamable HTTP options.

nodestdio477 GitHub stars