TheCocktailDB MCP for AI. Instantly find ingredients and mixing instructions for any drink.

Q: What if I want to find drinks using Gin? Do I use findcocktailsbyingredient?

Yes. You run findcocktailsbyingredient and pass in 'Gin'. This tool automatically queries the entire database and returns every single cocktail that contains gin.

Q: Can I use getrandomcocktail for inspiration?

Absolutely. If your users are stuck, running getrandomcocktail gives them a complete recipe suggestion instantly, perfect for a 'What should I drink?' widget.

Q: Can findcocktailsbyingredient handle mixers or liqueurs like Champagne?

Yes, you can use findcocktailsbyingredient for a wide range of inputs. While it covers major spirits (Vodka, Gin), it also indexes popular additions and modifiers to locate relevant recipes.

Q: After running searchcocktails, how do I get the full steps using getcocktaildetails?

You first run searchcocktails to find your drink and retrieve its unique CocktailDB ID. Then, you pass that specific ID directly into getcocktaildetails. This guarantees you pull the complete, verified recipe instructions.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

TheCocktailDB. Access 600+ global cocktail recipes through one API endpoint. Use your AI client to search for drinks by name, filter ingredients (Vodka, Gin, Rum, etc.), browse types (Shot, Punch), or get step-by-step mixing instructions and glass guides instantly.

What your AI can do

Browse cocktail category

Lists all available cocktail recipes filtered by a specific type, like 'Shot' or 'Punch/Party Drink'.

Find cocktails by ingredient

Retrieves every recipe that uses one or more specified alcoholic ingredients.

Get cocktail details

Fetches the full, specific details for a cocktail using its unique database ID.

+ 2 more capabilities included

Find recipes by name

You tell the agent a cocktail name (like 'Mojito'), and it returns the full recipe, ingredients, and mixing steps.

Search cocktails by ingredient

You give the agent a spirit or mix component (e.g., 'Gin'), and it lists every cocktail that uses it.

Browse drinks by type

You tell the agent you want to look at all 'Shots' or 'Coffee/Tea' recipes, and it pulls a list from those categories.

Get full recipe details

Using a specific CocktailDB ID, the agent retrieves the complete, precise recipe record for that drink.

Generate random ideas

You ask for inspiration, and the agent pulls a completely random cocktail recommendation.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

TheCocktailDB: 5 Tools for Mixology Data

These five tools let you search, filter, browse, and retrieve specific cocktail recipes from a global database using structured API calls.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using TheCocktailDB on Vinkius

Browse Cocktail Category

Lists all available cocktail recipes filtered by a specific type, like 'Shot' or 'Punch/Party Drink'.

Find Cocktails By Ingredient

Retrieves every recipe that uses one or more specified alcoholic ingredients.

Get Cocktail Details

Fetches the full, specific details for a cocktail using its unique database ID.

Get Random Cocktail

Provides an immediate, randomized recipe suggestion when inspiration is needed.

Search Cocktails

Searches and returns full recipes—ingredients, measures, steps, and glass type—based...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The TheCocktailDB integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "thecocktaildb": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the TheCocktailDB tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"thecocktaildb": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with TheCocktailDB, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by TheCocktailDB. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 5 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Building a menu section used to take hours of API mapping.

Today, if you wanted to build a page dedicated solely to 'Whiskey Cocktails,' your dev team would have to manually cross-reference dozens of recipes across multiple databases. They'd check for every mention of whiskey, filter out the irrelevant entries, and then structure the results—a process prone to missing data or broken links.

With TheCocktailDB MCP Server, you just tell the agent: 'Show me all cocktails using Whiskey.' You run `find_cocktails_by_ingredient`. It handles the entire database query. What you get back is a clean, structured list of working recipes and ingredients.

TheCocktailDB MCP Server gives you full recipe details instantly.

Before this, if your app needed the precise mixing instructions for an Old Fashioned, you might find a vague description or just the ingredients. You'd have to guess the measurements (1 oz? 1.5 oz?) and manually write out the steps.

Now, use `search_cocktails`. It returns not only the ingredients but also exact measures ('1½ oz Tequila') and step-by-step mixing instructions. The data is complete; you just display it.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

You're dealing with cocktails. This server gives your AI client direct access to a massive library—over 600 global recipes. It’s not just a list; it's actionable mixology data, letting you build drinks or figure out what ingredients you have on hand.

If you know the drink name, you use the search_cocktails tool. You feed it the cocktail title—say, 'Mojito'—and it immediately spits out the full recipe record. That includes the specific ingredient list, precise measurements for every item, step-by-step mixing instructions, and even what kind of glass you need. It handles all that complex output in one shot.

Need a different way to find something? If you've got a spirit like Gin or Vodka, run find_cocktails_by_ingredient. You give it the base component, and it returns every single recipe across the entire database that uses that specific ingredient. It’s perfect for inventory checks.

Want to browse by drink style instead? Just use browse_cocktail_category and tell your agent whether you're looking at 'Shots,' or maybe a complex 'Punch/Party Drink.' It filters the whole collection down to just those types of recipes.

If you already have a unique database ID for a cocktail, skip the searching and use get_cocktail_details. This tool fetches the complete, granular recipe record—the full truth about that single drink. You'll get every detail stored in its dedicated file.

Can't make up your mind? If you just need inspiration, ask for a random suggestion. The get_random_cocktail function pulls an immediate recommendation from the whole collection so you don’t have to do any searching at all.

It's built for efficiency. You tell it what you want—by name, by ingredient, or by category—and your agent handles the rest of the data retrieval. It keeps everything clean and focused on the recipe itself.

Built · Hosted · Managed by Vinkius TheCocktailDB MCP Server - Cocktail Recipes & Ingredients

Server ID 019d7575-ddd4-725a-a0a8-ffc5fc31334a

Vinkius Inspector

Compliance Grade D

Score 56.75/100

Report View Report ↗

Here's how it actually works

The bottom line is you skip manual research. You tell your agent what data point matters—an ingredient, a name, or a category—and it delivers the recipe details directly.

Start by telling your AI client what you're looking for (e.g., 'I need a drink using whiskey').

The agent selects and calls the appropriate tool, like find_cocktails_by_ingredient, passing in 'whiskey'.

It returns a structured list of cocktails that match the criteria, including full recipes when requested.

Who is this actually for?

Hospitality tech developers and mixology content creators use this tool daily. They're the people building apps that need reliable drink data without manual entry. If you build a cocktail app or a restaurant menu system, this saves hours of API mapping and ensures your recipes are always accurate.

App Developer (Hospitality)

Integrating a real-time recipe lookup into a client-facing mobile app. They use search_cocktails to populate the main menu view.

Content Manager

Building educational content about spirits. They use find_cocktails_by_ingredient to prove every cocktail that features Champagne, for instance.

QA Tester (API)

Verifying data integrity across different categories. They cycle through browse_cocktail_category and get_cocktail_details to check edge cases.

What Changes When You Connect

Find recipes accurately. The search_cocktails tool handles the full recipe card, giving you ingredient lists, exact measurements, step-by-step instructions, and the correct glass type—all in one call.

Filter by core ingredients easily. Instead of general searching, use find_cocktails_by_ingredient to pull a definitive list of every drink that uses a specific spirit like Rum or Tequila.

Support diverse content types. The browse_cocktail_category tool lets you organize content by type (Shot, Punch, Coffee/Tea), making your app's navigation clean and predictable.

Never run out of ideas. If the user is stuck on 'what to drink,' running get_random_cocktail provides an immediate, functional suggestion that needs zero user input.

Maintain data accuracy. The get_cocktail_details tool lets you pull precise records using a known ID, which is vital for automated inventory or content validation.

See it in action

01 01

Creating a themed menu section

A bar owner needs to populate a 'Tequila Cocktails' section. Instead of manually listing them, they use the agent with find_cocktails_by_ingredient and pass in 'Tequila'. The system immediately returns all relevant recipes for that section.

02 02

Writing an article about drink types

A food blogger is writing a piece on 'Party Drinks.' They use browse_cocktail_category and select 'Punch/Party Drink'. This generates a list of examples, which the agent then uses with search_cocktails to grab full recipes for inclusion.

03 03

Quickly solving a customer's query

A bartender answers a customer who just says 'something tropical.' The agent runs get_random_cocktail and suggests a recipe. The output gives the full ingredient list, allowing the bartender to start making it immediately.

04 04

Validating API content

A developer needs to check if the database has a perfect record for an old drink called 'Blue Lagoon.' They use get_cocktail_details with the known ID. This guarantees they get the full, authoritative data set without ambiguity.

The honest tradeoffs

Searching by vague concept

Anti-pattern

User asks: 'Give me a good drink.' The agent tries to run search_cocktails but gets generic, unhelpful results because no parameters were provided.

The Fix

Don't leave it open. If the user is unsure, guide them first with get_random_cocktail. If they know an ingredient, use find_cocktails_by_ingredient to narrow the focus.

Trying to guess a recipe

Anti-pattern

User inputs: 'Tequila lime juice salt.' The agent can't process this because it expects a specific cocktail name, not just ingredients.

The Fix

You have to use the tools. If you know an ingredient, run find_cocktails_by_ingredient. This tool handles multiple spirits and will tell you which recipes actually combine those components.

Over-relying on general search

Anti-pattern

Using only search_cocktails for everything. If the user is looking for a category (like 'Shots'), the search tool might miss it entirely.

The Fix

Use browse_cocktail_category first. This function guarantees you see all recipes in that specific grouping, which general searches often overlook.

When It Fits, When It Doesn't

Use this server when your primary need is retrieving structured cocktail data (ingredients, measures, steps). If the user query involves a known component—like 'Gin' or 'Whiskey'—start with find_cocktails_by_ingredient. This is the most targeted approach. Use search_cocktails only if you know the exact name of the drink. Don't use general searching for categories; instead, run browse_cocktail_category to ensure comprehensive coverage by type (e.g., 'Shot'). If the user needs inspiration, always default to get_random_cocktail. Only use get_cocktail_details if you already have the unique CocktailDB ID in hand. Don't try to combine ingredients and names into one general search; the specialized tools handle those cross-references for reliability.

Questions you might have

How do I use `search_cocktails`? +

You simply provide the name of the drink (e.g., 'Mai Tai'). It returns a full recipe card with ingredients, measures, mixing steps, and glass type.

What if I want to find drinks using Gin? Do I use `find_cocktails_by_ingredient`? +

Yes. You run find_cocktails_by_ingredient and pass in 'Gin'. This tool automatically queries the entire database and returns every single cocktail that contains gin.

Can I use `get_random_cocktail` for inspiration? +

Absolutely. If your users are stuck, running get_random_cocktail gives them a complete recipe suggestion instantly, perfect for a 'What should I drink?' widget.

Do I need to know the ID before using `get_cocktail_details`? +

Yes. This tool requires the specific CocktailDB ID to work. If you don't have the ID, first use search_cocktails or find_cocktails_by_ingredient to get it.

How do I browse by drink type with `browse_cocktail_category`? +

You call the tool and specify a category like 'Shot' or 'Punch/Party Drink.' It returns all recipes that fall under that specific classification.

How do I get specific measurements and glass types using `search_cocktails`? +

The search results include precise metrics for every ingredient, such as '1½ oz Tequila,' and specify the correct glassware. This means your agent provides accurate mixing ratios and presentation instructions.

Can `find_cocktails_by_ingredient` handle mixers or liqueurs like Champagne? +

Yes, you can use find_cocktails_by_ingredient for a wide range of inputs. While it covers major spirits (Vodka, Gin), it also indexes popular additions and modifiers to locate relevant recipes.

After running `search_cocktails`, how do I get the full steps using `get_cocktail_details`? +

You first run search_cocktails to find your drink and retrieve its unique CocktailDB ID. Then, you pass that specific ID directly into get_cocktail_details. This guarantees you pull the complete, verified recipe instructions.

Do I need an API key? +

No. TheCocktailDB provides free open access. No registration or API key required.

Are measurements standardized across all recipes? +

Measurements on TheCocktailDB typically default to imperial measurements (oz, parts, dashes). They match exactly what the database provides.

Can I search for non-alcoholic mocktails? +

Definitely! The DB maintains a 'Non-Alcoholic' category you can filter by when asking for a refreshing drink with zero ABV.

Connect to your AI in seconds.

Browse cocktail category

Find cocktails by ingredient

Get cocktail details

TheCocktailDB: 5 Tools for Mixology Data

Make your AI actually useful.

Browse Cocktail Category

Find Cocktails By Ingredient

Get Cocktail Details

Get Random Cocktail

Search Cocktails

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Building a menu section used to take hours of API mapping.

TheCocktailDB MCP Server gives you full recipe details instantly.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Creating a themed menu section

Writing an article about drink types

Quickly solving a customer's query

Validating API content

The honest tradeoffs

Searching by vague concept

Trying to guess a recipe

Over-relying on general search

When It Fits, When It Doesn't

Questions you might have