Tandoor MCP Server

What is Tandoor MCP Server?

A Model Context Protocol (MCP) server that enables AI assistants to interact with a Tandoor Recipe Manager instance. It provides tools for managing recipes, meal plans, and shopping lists.

How to use Tandoor MCP Server?

Install dependencies (npm install), build the server (npm run build), set the TANDOOR_URL and TANDOOR_API_TOKEN environment variables, and run node build/index.js. Then configure the server in your MCP settings file with the command, args, and env variables.

Key features of Tandoor MCP Server

• Create recipes with ingredients and instructions
• Add recipes to meal plans for specific dates and meal types
• Search recipes by name, keywords, foods, or rating
• Retrieve meal plans filtered by date range and meal type
• Get full details for a specific recipe
• List meal types, keywords, foods, and units
• View, add, update, and remove shopping list items

Use cases of Tandoor MCP Server

• Let an AI assistant add new recipes to your Tandoor collection
• Plan weekly meals by adding recipes to the meal plan
• Generate and manage a shopping list from meal plans
• Search and retrieve recipe details for cooking guidance

FAQ from Tandoor MCP Server

What are the system dependencies?

Node.js is required. The server uses npm for package management and a build step.

How do I authenticate with my Tandoor instance?

Set the TANDOOR_API_TOKEN environment variable to a valid API token from your Tandoor instance.

How is the server accessed by the AI?

It communicates over standard input/output (stdio) using the Model Context Protocol. No network port is exposed.

Can I test the server without an MCP client?

Yes, a test script is included. Run npm run test after setting your API token to verify tool functionality.

What tool operations can be auto-approved?

The README lists all tools as candidates for autoApprove in the MCP settings, including recipe and meal plan creation, retrieval, and shopping list management.