Mealie MCP Server
Allows saving recipes directly to a Mealie instance, automatically converting schema.org/Recipe format to Mealie's format and handling the two-step API workflow (create + update) with support for ingredients, instructions, nutrition info, and more.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Mealie MCP ServerSave this chocolate chip cookie recipe to my Mealie."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mealie MCP Server
A Model Context Protocol (MCP) server that allows LLMs to save recipes directly to your Mealie instance. This server accepts recipes in schema.org/Recipe format and handles the conversion and saving to Mealie automatically.
Features
Accepts recipes in standard schema.org/Recipe format
Automatically converts to Mealie's recipe format
Two-step API workflow (create + update) handled transparently
Supports ingredients, instructions, nutrition info, and more
Automatic field normalization (referenceId, display fields, etc.)
Proper error handling with descriptive messages
Current Limitations
Categories and Tags: Due to Mealie API limitations, categories and tags are not saved automatically. They must be created manually in the Mealie web UI before they can be assigned to recipes. See CATEGORIES_TAGS_LIMITATION.md for details.
Related MCP server: Mealie MCP Server
Installation
Clone this repository:
cd mealie-mcpInstall dependencies:
npm installBuild the project:
npm run buildConfiguration
Create a configuration file named .mealie-mcp.json in the project directory:
cp .mealie-mcp.json.example .mealie-mcp.jsonThen edit .mealie-mcp.json with your Mealie instance details:
{
"mealieUrl": "https://your-mealie-instance.com",
"apiToken": "your-api-token-here"
}Getting Your Mealie API Token
Log into your Mealie instance
Navigate to
/user/profile/api-tokensCreate a new API token
Copy the token to your configuration file
Note: The server looks for .mealie-mcp.json in the current working directory when it starts.
Usage with Claude Desktop
Add this server to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"mealie": {
"command": "node",
"args": ["/absolute/path/to/mealie-mcp/build/index.js"],
"cwd": "/absolute/path/to/mealie-mcp"
}
}
}Replace /absolute/path/to/mealie-mcp with the actual path to this project.
Important: The cwd (current working directory) must be set to the project directory so the server can find the .mealie-mcp.json configuration file.
Usage Examples
Once configured, you can ask Claude to save recipes to Mealie:
Example 1: Simple Recipe
Save this recipe to Mealie:
Chocolate Chip Cookies
Ingredients:
- 2 cups flour
- 1 cup butter
- 1 cup sugar
- 2 eggs
- 2 cups chocolate chips
Instructions:
1. Preheat oven to 350°F
2. Mix butter and sugar
3. Add eggs and flour
4. Fold in chocolate chips
5. Bake for 12 minutesExample 2: Detailed Recipe
Save this pasta recipe to Mealie:
Name: Classic Spaghetti Carbonara
Cuisine: Italian
Category: Main Course
Prep Time: 10 minutes
Cook Time: 20 minutes
Servings: 4
Ingredients:
- 400g spaghetti
- 200g guanciale or pancetta
- 4 egg yolks
- 100g Pecorino Romano cheese
- Black pepper
- Salt
Instructions:
1. Cook pasta in salted boiling water until al dente
2. Cut guanciale into small pieces and cook until crispy
3. Mix egg yolks with grated cheese
4. Combine hot pasta with guanciale
5. Remove from heat and mix in egg mixture
6. Season with black pepper and serve
Tags: italian, pasta, quick-mealsRecipe Format
The MCP tool accepts recipes in schema.org/Recipe format with the following fields:
Required
name: Recipe name
Optional
description: Recipe descriptionrecipeYield: Number of servings (e.g., "4 servings")totalTime: Total time (ISO 8601 duration, e.g., "PT30M")prepTime: Preparation time (ISO 8601 duration)cookTime: Cooking time (ISO 8601 duration)recipeCategory: Category or array of categories ⚠️ Not currently saved (see limitations)recipeCuisine: Cuisine typekeywords: Tags/keywords (string or array) ⚠️ Not currently saved (see limitations)recipeIngredient: Array of ingredient stringsrecipeInstructions: String or array of instruction objectsnutrition: Object with nutritional informationimage: Image URL or array of URLsurl: Original source URLaggregateRating: Rating information
Development
Run in development mode:
npm run devBuild the project:
npm run buildProject Structure
mealie-mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── config.ts # Configuration management
│ ├── types.ts # TypeScript interfaces
│ ├── converter.ts # Schema.org to Mealie converter
│ ├── converter.test.ts # Converter tests
│ ├── mealie-client.ts # Mealie API client
│ └── mealie-client.test.ts # Integration tests
├── build/ # Compiled JavaScript
├── MEALIE_API_STRUCTURE.md # API format documentation
├── CATEGORIES_TAGS_LIMITATION.md # Categories/tags limitation details
├── package.json
├── tsconfig.json
└── README.mdTroubleshooting
Error: Config file not found
Ensure
.mealie-mcp.jsonexists in the project directoryCheck that the JSON is valid
Verify both
mealieUrlandapiTokenare presentIf using Claude Desktop, ensure the
cwdis set correctly in the config
Error: Failed to create recipe (401)
Your API token is invalid or expired
Generate a new token in Mealie at
/user/profile/api-tokens
Error: Failed to create recipe (404)
Check that your
mealieUrlis correctEnsure the URL does not have a trailing slash
Verify your Mealie instance is accessible
Recipe created but update failed
The recipe was created in Mealie but detailed information failed to save
Check the slug mentioned in the error and manually update in Mealie if needed
Categories or tags not showing up
Categories and tags must be created manually in Mealie first
Navigate to Settings → Categories/Tags in your Mealie instance
Create the categories/tags you want to use
See CATEGORIES_TAGS_LIMITATION.md for more details
How It Works
The server handles the complete workflow automatically:
Schema.org Input: LLM provides recipe in standard schema.org format
Conversion: Converts to Mealie's internal format
Create:
POST /api/recipeswith just the recipe name → returns a slugNormalize: Automatically adds all required Mealie fields:
Generates
referenceId(UUID) for each ingredientSets
display,unit,food,isFood,disableAmountfieldsAdds
titleandingredientReferencesto instructionsRemoves categories/tags (Mealie API limitation)
Update:
PATCH /api/recipes/{slug}with complete recipe data
If the update fails, the recipe will exist in Mealie with just a name and can be edited manually.
For detailed information about the data structure, see MEALIE_API_STRUCTURE.md.
Documentation
MEALIE_API_STRUCTURE.md - Detailed explanation of Mealie's recipe format, the data workflow, and known issues
CATEGORIES_TAGS_LIMITATION.md - Why categories and tags aren't saved and how to work around it
Testing
Run integration tests (requires .mealie-mcp.json configuration):
npm testRun converter tests only:
npm test -- converter.testLicense
ISC
Contributing
Issues and pull requests are welcome!
Available Tools
1 toolsave_recipeB
Save a recipe to Mealie. Accepts a recipe in schema.org/Recipe format and saves it to your Mealie instance.
| Name | Required | Description | Default |
|---|---|---|---|
| recipe | Yes | Recipe in schema.org/Recipe format |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only says 'Save' and 'saves it', which implies a write operation but does not explain if it updates existing recipes, what happens on duplicates, authentication requirements, rate limits, or any side effects. This is a significant transparency gap for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, front-loaded with the action. However, the second clause ('saves it to your Mealie instance') repeats information from the first clause ('Save a recipe to Mealie'), making it slightly redundant. It is still concise and well-structured, just with minor redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a complex nested schema with many fields, no annotations, and no output schema. The description covers only the basic action and format, but does not explain return behavior, error handling, or idempotency. Given the rich schema, the description is minimally viable but lacks important context for a mutation operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents the 'recipe' parameter and all its nested properties. The description only restates the schema's top-level comment ('Accepts a recipe in schema.org/Recipe format'), adding no new semantics. Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Save'), identifies the resource ('a recipe to Mealie'), and clearly states the input format ('schema.org/Recipe format'). It fully distinguishes the tool's function even without sibling tools, as it names the destination system (Mealie) and the action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool should be used when you have a recipe object in schema.org format, but it does not provide explicit guidance on when to use it versus alternatives, nor does it state any prerequisites or exclusions. Since there are no sibling tools, the lack of alternatives comparison is less critical, but it falls short of explicit usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
save_recipe
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity. The tool's purpose is clear and distinct.
The single tool 'save_recipe' follows a consistent verb_noun naming pattern, which is clear and predictable.
Only one tool is provided, which is far too few for a Mealie server that typically requires operations like listing, retrieving, updating, and deleting recipes. This severely limits the server's utility.
The server covers only the save operation, with no way to read, update, delete, or list recipes. This represents a severely incomplete surface for recipe management and creates dead ends for agents.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Search, save, organize, cook, and share recipes with any AI assistant.
Scraps Kitchen gives any AI agent a persistent, household-aware kitchen memory. Unlike generic chatbot recall, Scraps maintains structured cooking data: what's in your fridge (with freshness tracking), who you cook for (with allergens, dietary restrictions, and preferences), your recipe collection (with cook notes and per-diner ratings), your shopping list, and your kitchen equipment. 27 tools across 6 domains let agents read kitchen context, suggest meals that respect dietary safety, update the pantry after cooking, and build a history of what works for your household. Every interaction makes the data richer. Cooking history, preference signals, kitchen awareness = better suggestions next time. All tools work via oAuth and a free scraps.kitchen account.
Household-aware cooking brain: pantry, meal suggestions, dietary safety, recipes, shopping lists.
- ZelesIAOAuthcom.zelesia
Turn the LinkedIn posts you save into a knowledge base your assistant can search and cite.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to interact with Mealie recipe databases through MCP clients like Claude Desktop.134MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Mealie for recipe management, meal planning, and shopping list operations. Supports searching and managing recipes, creating meal plans, and generating shopping lists from recipes or meal plans.7MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to interact with Mealie recipe databases, allowing users to manage and query their recipes through natural language conversations.16MIT
- AlicenseNot gradedqualityDmaintenanceExposes Mealie recipe manager as LLM-callable tools for searching recipes, managing meal plans, and editing shopping lists.MIT