A high-performance cocktail search and recipe retrieval server that integrates with Bar Assistant instances to provide intelligent cocktail discovery through natural language queries.
🔍 Smart Cocktail Search - Natural language queries with similarity matching for finding drinks by name, ingredient, base spirit, flavor profile, or ABV. Filter by ABV ranges, glassware types, preparation methods, alcohol strength preferences (light/medium/strong), and flavor profiles (bitter/sweet/sour/spicy/herbal). Returns complete recipes with auto-converted measurements, step-by-step instructions, and specifications.
📖 Recipe Retrieval - Single or batch lookup by name or database ID with flexible mixing of both. Retrieve up to 20 recipes simultaneously with parallel processing for 5-10x performance improvement. Includes detailed ingredients with precise measurements, instructions, ABV, glassware, garnishes, and direct database links. Optionally include similar cocktails and variations for exploration.
🧪 Ingredient Intelligence - Comprehensive ingredient research including descriptions, flavor profiles, tasting notes, substitution guidance with flavor impact analysis, and complete recipes featuring the ingredient.
⚡ Performance Features - Parallel API processing, intelligent caching system with 70%+ hit rate (<50ms for cached responses), error resilience where individual failures don't break batch operations, configurable limits (up to 50 search results, 20 recipes), and detailed performance metrics tracking.
Use Cases: "What cocktails can I make with gin and vermouth?", "Show me the recipe for a Manhattan", "Find bitter cocktails with ABV over 25%", "What is Campari and what can I make with it?", "Give me cocktails like a Negroni"
Enables natural language interactions with Bar Assistant cocktail databases, allowing queries for cocktail recipes, ingredient searches, and recommendations through AI assistants.
Bar Assistant MCP Server
A high-performance Model Context Protocol (MCP) server that provides intelligent cocktail search and recipe retrieval from Bar Assistant instances.
Features
🔍 Smart Cocktail Search - Natural language queries with similarity matching
📖 Complete Recipes - Detailed ingredients, instructions, and specifications
🎯 Similarity Engine - Discover cocktails similar to your favorites
🧪 Ingredient Analysis - Find cocktails by ingredients, flavors, and characteristics
⚡ Batch Processing - Retrieve multiple recipes simultaneously (5-10x faster)
💾 Smart Caching - Intelligent caching with 70%+ hit rate
🔧 Advanced Filtering - ABV ranges, glassware, preparation methods, and more
Prerequisites
Docker and Docker Compose
Access to a Bar Assistant instance
Bar Assistant API token
Running with Docker
The only supported method for running the server is with Docker Compose.
Create an
Create a file named
.envin the root of the project and add the following, replacing the placeholder values with your actual Bar Assistant configuration:BAR_ASSISTANT_URL=https://your-instance.com BAR_ASSISTANT_TOKEN=your-api-token BAR_ASSISTANT_BAR_ID=1Get Your Bar Assistant API Token:
Log into your Bar Assistant instance
Navigate to Settings → API
Generate a new API token
Copy the token and paste it into the
BAR_ASSISTANT_TOKENfield in your.envfile.
Build and start the container:
docker-compose up --build -dThe server will be available at
http://localhost:3001.
Usage
Once configured, you can interact with the server through your MCP client. Here are some example queries:
"What cocktails can I make with gin and vermouth?"
"Show me the recipe for a Manhattan"
"Give me recommendations on cocktails like a Negroni"
"What ingredients do I need to buy to make these 5 cocktails?"
"Show me how to make a Manhattan"
"What cocktails can I make with gin and vermouth?"