Bar Assistant MCP Server
Enables management of your home bar inventory and cocktail discovery through Bar Assistant. View shelf ingredients, find cocktails you can make, and add or remove items from your bar collection.
README
Bar Assistant MCP Server
An MCP (Model Context Protocol) server for Bar Assistant - manage your home bar shelf and discover cocktails you can make.
Features
- ๐ View ingredients on your bar shelf
- ๐ธ See cocktails you can make with what you have
- โ Add ingredients to your shelf
- โ Remove ingredients from your shelf
- ๐ Search for ingredients by name
- ๐ช Discover your available bars
- ๐งช Create new ingredients
- ๐น Create new cocktail recipes
- โ๏ธ Update existing cocktail recipes
Installation
Using uvx (Recommended)
Run directly with uvx:
uvx --from git+https://github.com/the-real-py/bar-assistant-mcp bar-assistant-mcp \
https://bar.johnprovost.com/bar/api \
your_token_here \
1
Or set environment variables in .env and run:
uvx --from git+https://github.com/the-real-py/bar-assistant-mcp bar-assistant-mcp
Using pip
pip install git+https://github.com/the-real-py/bar-assistant-mcp
bar-assistant-mcp
Configuration
Create a .env file in your project directory:
BAR_ASSISTANT_API_URL=https://bar.johnprovost.com/bar/api
BAR_ASSISTANT_TOKEN=your_bearer_token_here
BAR_ASSISTANT_BAR_ID=1
Or pass them as command-line arguments:
bar-assistant-mcp <api_url> <token> <bar_id>
Getting Your Credentials
- API URL: Your Bar Assistant instance URL + the API path
- Standard setup:
http://localhost:8000/api - Custom setup: Check your reverse proxy configuration (e.g.,
https://bar.example.com/bar/api)
- Standard setup:
- Token: Generate a personal access token from your Bar Assistant profile settings
- Bar ID: Use the
list_barstool to find your bar ID, or it's usually1for your first bar
Important: The BAR_ASSISTANT_BAR_ID is optional. If you don't set it, you can provide the bar_id parameter when calling tools, or use the list_bars tool first to discover your available bars.
Usage with Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"bar-assistant": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/the-real-py/bar-assistant-mcp",
"bar-assistant-mcp",
"https://bar.johnprovost.com/bar/api",
"your_token_here",
"1"
]
}
}
}
Or using environment variables:
{
"mcpServers": {
"bar-assistant": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/the-real-py/bar-assistant-mcp",
"bar-assistant-mcp"
],
"env": {
"BAR_ASSISTANT_API_URL": "https://bar.johnprovost.com/bar/api",
"BAR_ASSISTANT_TOKEN": "your_token_here",
"BAR_ASSISTANT_BAR_ID": "1"
}
}
}
}
Available Tools
list_bars
Discover all bars you have access to and get their IDs.
get_shelf_ingredients
List all ingredients on your bar shelf.
Parameters:
bar_id(optional): Bar ID to querypage(optional): Page number for pagination
get_shelf_cocktails
See all cocktails you can make with your current ingredients.
Parameters:
bar_id(optional): Bar ID to querypage(optional): Page number for pagination
add_ingredients_to_shelf
Add ingredients to your shelf by their IDs.
Parameters:
ingredient_ids(required): Array of ingredient IDsbar_id(optional): Bar ID to update
remove_ingredients_from_shelf
Remove ingredients from your shelf.
Parameters:
ingredient_ids(required): Array of ingredient IDsbar_id(optional): Bar ID to update
search_ingredients
Search for ingredients by name to find their IDs.
Parameters:
name(required): Ingredient name to search forbar_id(optional): Bar ID context
create_ingredient
Create a new ingredient in the bar database. Use this when an ingredient doesn't exist and needs to be created before adding to a cocktail.
Parameters:
name(required): Name of the ingredientstrength(optional): Alcohol strength/percentage (e.g., 40 for 40% ABV)description(optional): Description of the ingredientorigin(optional): Origin/country of the ingredientcolor(optional): Hex color code (e.g., '#ffffff')parent_ingredient_id(optional): Parent ingredient ID for categorizationunits(optional): Default units for this ingredient (e.g., 'ml', 'oz', 'dash')bar_id(optional): Bar ID context
create_cocktail
Create a new cocktail recipe. First use search_ingredients to find ingredient IDs, then use create_ingredient for any missing ingredients.
Parameters:
name(required): Name of the cocktailinstructions(required): Step-by-step instructions for making the cocktailingredients(required): Array of ingredients with:ingredient_id(required): ID of the ingredientamount(required): Amount of the ingredientunits(optional): Units for the amount (e.g., 'ml', 'oz', 'dash')optional(optional): Whether this ingredient is optionalnote(optional): Additional note for this ingredientsort(optional): Sort order for the ingredient
description(optional): Description of the cocktailgarnish(optional): Garnish for the cocktailsource(optional): Source/origin of the recipeglass_id(optional): ID of the glass type to usemethod_id(optional): ID of the mixing method (shaken, stirred, etc.)tags(optional): Array of tags for the cocktailbar_id(optional): Bar ID context
Example - Creating a Margarita:
1. search_ingredients(name="tequila") โ ID: 45
2. search_ingredients(name="lime juice") โ ID: 89
3. search_ingredients(name="triple sec") โ ID: 23
4. create_cocktail(
name="Margarita",
instructions="1. Add all ingredients to shaker with ice\n2. Shake well\n3. Strain into salt-rimmed glass",
ingredients=[
{"ingredient_id": 45, "amount": 60, "units": "ml"},
{"ingredient_id": 89, "amount": 30, "units": "ml"},
{"ingredient_id": 23, "amount": 30, "units": "ml"}
],
garnish="Lime wheel, salt rim"
)
update_cocktail
Update an existing cocktail recipe. Use this to modify the name, instructions, ingredients, or other details of a cocktail.
Parameters:
id(required): ID of the cocktail to updatename(required): Name of the cocktailinstructions(required): Step-by-step instructions for making the cocktailingredients(required): Array of ingredients with:ingredient_id(required): ID of the ingredientamount(required): Amount of the ingredientunits(optional): Units for the amount (e.g., 'ml', 'oz', 'dash')optional(optional): Whether this ingredient is optionalnote(optional): Additional note for this ingredientsort(optional): Sort order for the ingredient
description(optional): Description of the cocktailgarnish(optional): Garnish for the cocktailsource(optional): Source/origin of the recipeglass_id(optional): ID of the glass type to usemethod_id(optional): ID of the mixing method (shaken, stirred, etc.)tags(optional): Array of tags for the cocktailbar_id(optional): Bar ID context
Resources
bar://shelf/ingredients- Your bar shelf ingredientsbar://shelf/cocktails- Cocktails you can make
Development
Clone and install in development mode:
git clone https://github.com/the-real-py/bar-assistant-mcp
cd bar-assistant-mcp
pip install -e .
Troubleshooting
Finding Your API URL
The Bar Assistant API URL depends on your setup:
- Standard Docker setup:
http://localhost:8000/api - Custom reverse proxy: Check your nginx/Traefik configuration for the API route
- Cloud hosted: Usually provided by your hosting service
To verify your API URL is correct, run:
curl -H "Accept: application/json" YOUR_API_URL/server/version
You should get a JSON response with version information.
License
MIT
Links
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.