Cocktail Recipe Data for AI Agents

Overview

Cocktail works by querying a large database of cocktail recipes to retrieve the ingredients, instructions, and other details of a cocktail. It returns the cocktail recipe in a structured format.

Live Test Cocktail Recipe Data for AI Agents Source →

The tool

Once your client is connected to the VerveContext server, this appears in its tool list as CocktailRecipeDataforAIAgents. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

Tool call

{
  "name": "CocktailRecipeDataforAIAgents",
  "arguments": {
    "name": "martini"
  }
}

You do not name the tool yourself; the model picks it. Asking about martini in the terms this source covers is enough for it to reach for CocktailRecipeDataforAIAgents on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every source in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervecontext": {
      "url": "https://api.vervecontext.com/v1/mcp"
    }
  }
}

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

Argument	Type	Description
`name`Required	string	The name of the cocktail for which you want to get the recipe (e.g., martini) length 0–100

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "count": 5,
    "filteredOn": "name",
    "cocktails": [
      {
        "name": "Espresso Martini",
        "glass": "martini",
        "category": "After Dinner Cocktail",
        "ingredients": [
          {
            "unit": "cl",
            "amount": 5,
            "ingredient": "Vodka"
          },
          {
            "unit": "cl",
            "amount": 1,
            "ingredient": "Coffee liqueur",
            "label": "Kahlúa"
          },
          {
            "special": "Sugar syrup (according to individual preference of sweetness)"
          },
          {
            "special": "1 short strong Espresso"
          }
        ],
        "ingredientCount": 4,
        "estimatedStrength": "medium",
        "preparation": "Shake and strain into a chilled cocktail glass."
      },
      {
        "name": "Lemon Drop Martini",
        "glass": "martini",
        "category": "All Day Cocktail",
        "ingredients": [
          {
            "unit": "cl",
            "amount": 2.5,
            "ingredient": "Vodka",
            "label": "Citron Vodka"
          },
          {
            "unit": "cl",
            "amount": 2,
            "ingredient": "Triple Sec"
          },
          {
            "unit": "cl",
            "amount": 1.5,
            "ingredient": "Lemon juice"
          }
        ],
        "garnish": "Lemon slice",
        "preparation": "Shake and strain into a chilled cocktail glass rimmed with sugar."
      },
      {
        "name": "French Martini",
        "glass": "martini",
        "category": "Before Dinner Cocktail",
        "ingredients": [
          {
            "unit": "cl",
            "amount": 4.5,
            "ingredient": "Vodka"
          },
          {
            "unit": "cl",
            "amount": 1.5,
            "ingredient": "Raspberry liqueur"
          },
          {
            "unit": "cl",
            "amount": 1.5,
            "ingredient": "Pineapple juice"
          }
        ],
        "preparation": "Stir in mixing glass with ice cubes. Strain into chilled cocktail glass. Squeeze oil from lemon peel onto the drink."
      },
      {
        "name": "Dirty Martini",
        "glass": "martini",
        "category": "Before Dinner Cocktail",
        "ingredients": [
          {
            "unit": "cl",
            "amount": 6,
            "ingredient": "Vodka"
          },
          {
            "unit": "cl",
            "amount": 1,
            "ingredient": "Vermouth",
            "label": "Dry vermouth"
          },
          {
            "unit": "cl",
            "amount": 1,
            "ingredient": "Olive juice"
          }
        ],
        "garnish": "Green olive",
        "preparation": "Stir in mixing glass with ice cubes. Strain into chilled martini glass."
      },
      {
        "name": "Dry Martini",
        "glass": "martini",
        "category": "Before Dinner Cocktail",
        "ingredients": [
          {
            "unit": "cl",
            "amount": 6,
            "ingredient": "Gin"
          },
          {
            "unit": "cl",
            "amount": 1,
            "ingredient": "Vermouth",
            "label": "Dry vermouth"
          }
        ],
        "preparation": "Stir in mixing glass with ice cubes. Strain into chilled martini glass. Squeeze oil from lemon peel onto the drink, or garnish with olive."
      }
    ]
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Field	Type	Example	Description
`count`	number	`5`	Number of cocktails returned
`filteredOn`	string	`name`	Which parameter the results were filtered by
`cocktails`	array[5]		The matching cocktail recipes
`cocktails.0.name`	string	`Espresso Martini`	Name of the cocktail
`cocktails.0.glass`	string	`martini`	Glass the cocktail is traditionally served in
`cocktails.0.category`	string	`After Dinner Cocktail`	Category the cocktail belongs to, such as after dinner or pre-dinner
`cocktails.0.ingredients`	array[4]		Ingredients with their measures
`cocktails.0.ingredients.0.unit`	string	`cl`	Unit the measure is given in, such as cl or dash
`cocktails.0.ingredients.0.amount`	number	`5`	How much of the ingredient to use
`cocktails.0.ingredients.0.ingredient`	string	`Vodka`	Name of the ingredient
`cocktails.0.ingredientCount`	number	`4`	Number of ingredients in the cocktail
`cocktails.0.estimatedStrength`Premium	string	`medium`	Alcohol strength estimate: strong, medium, light, or mocktail
`cocktails.0.preparation`	string	`Shake and strain into a chilled cocktail glass.`	How to make the cocktail

Why ground on it

A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value in a shape you can check, which is the difference between an answer you can cite and one you have to hedge.

Point an evaluation at count: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

Status	What it means
`400` / `422`	The arguments did not validate. The message names the offending one.
`401`	The OAuth session is invalid or expired — reconnect the server.
`403`	Blocked by a key restriction or an IP allow-list. Never a bad identity.
`404`	This source is not part of VerveContext. Check the catalog.
`429`	Out of credits, or a brief rate limit. The message tells them apart.

A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Bar Inventory Matching: Match available spirits against the ingredient search to show bartenders which drinks they can prepare with current bar stock.
Digital Drink Menus: Hospitality venues display drink preparation instructions and specific glassware recommendations directly on contactless tablet menus for guests.
Drink of the Day: To drive customer engagement, lifestyle apps fetch a random cocktail recipe each morning to feature on their home screen.
Event Menu Planning: Catering planners look up cocktail categories and measured ingredients to calculate supply quantities needed for upcoming wedding receptions.

Other ways to use Cocktail Recipe Data for AI Agents

Set up Cocktail Recipe Data for AI Agents on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an x-api-key header, with SDKs for Node, Python and .NET.APIVerve →Reference →

Give it to an AI agentConnect over MCP and your agent calls it as a native tool — Claude, Cursor, ChatGPT.VerveKit →Reference →

Google Sheets or ExcelA =VERVE() formula fills a column — no script, no export, recalculates in place.VerveSheets →Reference →