mealie-mcp

create_recipe

Create a new recipe in Mealie by specifying ingredients, instructions, servings, prep and cook times, categories, tags, and notes. Use this tool to manually add any recipe.

Instructions

Create a new recipe manually.

Args: name: Recipe name description: Short description recipe_yield: Yield description (e.g. "15–18 rolls", "1 loaf") servings: Numeric serving count that enables scaling (e.g. 6, 8, 15) total_time: Total time (e.g. "45 minutes") prep_time: Prep time perform_time: Cook time ingredients: List of ingredient dicts, each with optional keys: - section (str): creates a visual section header (no other fields used) - quantity (float): numeric amount (e.g. 300, 2.5) - unit (str): unit name or abbreviation (e.g. "g", "cup", "tbsp") - food (str): ingredient name (e.g. "bread flour", "butter") - comment (str): extra info shown alongside (e.g. "softened", "about 1¾ tsp") instructions: List of instruction steps — each may be a plain string or a dict with: - text (str): step body - title (str, optional): step heading shown in UI - summary (str, optional): one-line takeaway for cook mode - ingredient_refs (list[str], optional): UUIDs of linked ingredients categories: Category names to assign tags: Tag names to assign notes: List of note dicts, each with: - title (str): section label (e.g. "Non-Negotiables") - text (str): note body extras: Arbitrary JSON metadata (e.g. {"isFoundation": true})

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes
`tags`	No
`notes`	No
`extras`	No
`servings`	No
`prep_time`	No
`categories`	No
`total_time`	No
`description`	No
`ingredients`	No
`instructions`	No
`perform_time`	No
`recipe_yield`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 30, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that this creates a new recipe, and it also reveals useful parameter-level behaviors: servings enable scaling, section creates a visual header, summary is a one-line takeaway for cook mode. It does not mention edge behaviors like duplicate-name handling or whether categories/tags must already exist, but the provided details are substantial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but appropriately structured for a 13-parameter tool with nested objects. It front-loads the purpose, then organizes arguments in a readable list where every line adds semantic information, examples, or expected formats. There is no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high parameter count, dense nested structures, and 0% schema description coverage, the description is exceptionally complete. It documents all fields including optional sub-keys and examples, and since an output schema exists, the description need not explain return values. Only minor usage routing details are absent, and those are already captured in the usage guideline dimension.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must fully document every parameter. It does exactly that: each parameter has a type, a purpose, and often realistic examples. Nested structures for ingredients, instructions, notes, and extras are explained with optional keys and expected shapes, adding enormous value beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create a new recipe manually.' The word 'manually' distinguishes it from the sibling create_recipe_from_url, and the parameter list reinforces that this is for full manual entry rather than import or update.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'manually' provides clear context that this tool is for direct entry, implying the correct alternative for URL-based creation is create_recipe_from_url. However, it does not explicitly name siblings like update_recipe for modifying existing recipes or state when not to use this tool, so the guidance is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.