Save, search and import recipes, manage grocery lists and plan meals in Only Recipes.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Use this when the user shares a recipe link and you only need to know whether Only Recipes already has it. Returns the matching recipe's id, name and page, or exists: false. Fetches nothing. To show the recipe, use import_recipe instead.
The recipe's original web address
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http only-recipes https://onlyrecipes.app/mcp
Use this when the user shares a recipe link and you only need to know whether Only Recipes already has it. Returns the matching recipe's id, name and page, or exists: false. Fetches nothing. To show the recipe, use import_recipe instead.
| Argument | Type | Description |
|---|---|---|
| url* | string | The recipe's original web address |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The recipe's original web address"
}
}
}Use this when you need valid tag slugs for search_recipes, for example to filter by cuisine, course, diet or occasion. Without arguments returns every category with its tags; with category returns only that category's tags. Not needed for plain keyword searches. Without a linked account, the full list covers the featured categories and only tags that have public recipes.
| Argument | Type | Description |
|---|---|---|
| category | string | A category slug or id, e.g. 'cuisine' or 'diet'. Leave out to get all categories. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"category": {
"type": "string",
"description": "A category slug or id, e.g. 'cuisine' or 'diet'. Leave out to get all categories."
}
}
}Use this when the user wants to see or cook one specific recipe: its ingredients, steps, times and photo. Pass servings to scale every ingredient quantity. Takes an id or slug from another tool's results; for a pasted link use import_recipe. Without a linked account the recipe comes from the public recipe page's data: a few internal columns (video ids, short title, SEO title, bookmark/favorite/collection counts, site, cuisine and restaurant refs) come back null.
| Argument | Type | Description |
|---|---|---|
| servings | number | Scale the ingredients to this many servings. Leave out for the recipe as written. |
| identifier* | string | The recipe slug or ID (IDs start with 'rec_') |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"identifier"
],
"properties": {
"servings": {
"type": "number",
"maximum": 200,
"description": "Scale the ingredients to this many servings. Leave out for the recipe as written.",
"exclusiveMinimum": 0
},
"identifier": {
"type": "string",
"description": "The recipe slug or ID (IDs start with 'rec_')"
}
}
}Use this when the user pastes a recipe link (any recipe site, Instagram, TikTok, YouTube, Pinterest or Facebook) and wants the recipe itself. Returns clean ingredients and steps without ads. Does not add anything to the user's account; call save_recipe afterwards if they want to keep it. For recipe text pasted into the chat, use create_recipe instead.
| Argument | Type | Description |
|---|---|---|
| url* | string | The URL to import the recipe from |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The URL to import the recipe from"
}
}
}Use this when the user wants ideas or recipes to cook, by dish, ingredient, cuisine, diet, time or rating, or just wants to browse. query is optional: leave it out to browse by tags and sort. Searches the public Only Recipes library and returns a grid of recipes. Not for the user's own recipes (use list_my_recipes) or for a pasted link (use import_recipe). Plain keywords need no filters; call get_filters first only to filter by tag. Without a linked account, query matches whole words and word prefixes in the recipe name, a short description summary and tag slugs (not arbitrary substrings), results can lag new recipes and votes by up to a day, and sourceUrl is always null.
| Argument | Type | Description |
|---|---|---|
| page | integer | Page number (1-indexed, default 1) |
| sort | string | Sort order: recent (newest), popular (most votes), rating (highest rated), trending (recently imported) |
| tags | array | Tag slugs to filter by (e.g. ['italian', 'dinner', 'vegetarian']) |
| query | string | Text search query to match recipe name or description |
| pageSize | integer | Results per page (default 12, max 50) |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"page": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1,
"description": "Page number (1-indexed, default 1)"
},
"sort": {
"enum": [
"recent",
"popular",
"rating",
"trending"
],
"type": "string",
"description": "Sort order: recent (newest), popular (most votes), rating (highest rated), trending (recently imported)"
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tag slugs to filter by (e.g. ['italian', 'dinner', 'vegetarian'])"
},
"query": {
"type": "string",
"description": "Text search query to match recipe name or description"
},
"pageSize": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Results per page (default 12, max 50)"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 18, 2026.