Bar Assistant

You can run Bar Assistant MCP Server to query and retrieve cocktail recipes from Bar Assistant instances using a high-performance MCP interface. It supports natural language search, complete recipes, ingredient analysis, and batch processing, all served through a scalable HTTP MCP endpoint.

How to use

Connect your MCP client to the Bar Assistant MCP Server at the provided HTTP endpoint. You can ask for cocktails by ingredients, search strings like a Negroni, or request batch retrieval of several recipes. Use the same MCP client patterns you rely on for other servers, and take advantage of the server’s advanced filtering to narrow results by ABV, glassware, or preparation method. When you want recommendations similar to a favorite cocktail, ask for similar recipes and you will receive closely matched options.

Practical usage patterns you can try include: searching for cocktails using specific ingredients, requesting a full recipe with ingredients and steps, generating recommendations similar to a known drink, and compiling a shopping list for multiple cocktails. You can also perform batch queries to retrieve multiple recipes at once, speeding up workflows that require a large set of options.

How to install

Prerequisites you need before starting are Docker and Docker Compose, plus access to a Bar Assistant instance and its API token.

1. Create an environment file in the project root named .env and fill in your Bar Assistant configuration. Replace placeholders with your actual values:

BAR_ASSISTANT_URL=https://your-instance.com
BAR_ASSISTANT_TOKEN=your-api-token
BAR_ASSISTANT_BAR_ID=1

2. Obtain your Bar Assistant API token from your Bar Assistant account settings under API, then paste it into the BAR_ASSISTANT_TOKEN field in the .env file.

3. Build and start the container using Docker Compose.

docker-compose up --build -d

4. Verify the server is running by checking accessibility at http://localhost:3001 from your environment.

Advanced configuration and notes

Environment variables you set for Bar Assistant are required by the MCP server to connect to your Bar Assistant instance. The following variables are used by the server and should be included in your deployment: BAR_ASSISTANT_URL, BAR_ASSISTANT_TOKEN, and BAR_ASSISTANT_BAR_ID. Keep these values secure and do not expose them in public code or logs.

Security tip: restrict access to the MCP endpoint to trusted clients and consider using network-level access controls or a reverse proxy with authentication for production deployments.

If you need to reconfigure the Bar Assistant connection, update the .env file and restart the container with the same Docker Compose command to apply changes.

Configuration example

Below is a representative MCP connection configuration for the Bar Assistant server over HTTP. Use this as a guide when adding the server to your MCP client configuration.

{
  "mcpServers": {
    "bar_assistant": {
      "type": "http",
      "name": "bar_assistant",
      "url": "http://localhost:3001",
      "args": []
    }
  }
}

Available tools

Smart Cocktail Search

Perform natural language queries with similarity matching to find cocktails that fit your description or available ingredients.

Complete Recipes Retrieval

Fetch full recipes including ingredients, instructions, and specifications.

Similarity Engine

Discover cocktails that are similar to given favorites to broaden your mixology options.

Ingredient Analysis

Find cocktails by ingredients, flavor profiles, and characteristics.

Batch Processing

Retrieve multiple recipes simultaneously to speed up workflows.

Smart Caching

Leverage intelligent caching to reduce response times and increase hit rates.