Cocktail Glass

The fastest way in is theModel Context Protocol (MCP)server. It's a remote, stateless endpoint athttps://cocktail.glass/mcp. Point any MCP client at it and seven cocktail tools — plus a guided prompt — appear.

claude mcp add --transport http cocktail-glass https://cocktail.glass/mcp

{ "mcpServers": { "cocktail-glass": { "url": "https://cocktail.glass/mcp" } } }

That's it. No key to paste. The server exposes seven read-only tools —search_cocktails,list_cocktails,get_cocktail_recipe,find_cocktails_by_ingredient,find_cocktails_in_movie,find_makeable_cocktails, andrandom_cocktail— plus acocktails_from_my_barprompt.

Seven tools and a guided prompt cover the questions that come up around a home bar:

- “What can I make tonight?”Share the bottles you own — or a photo of your cabinet — and get back the cocktails you can make right now, plus the ones you're a single ingredient short of.
- “How do I make a Last Word?”A hands-free recipe reference while you're mixing: exact measures, glassware, steps, and garnish.
- “I bought a bottle of mezcal — now what?”Every cocktail that uses a spirit or liqueur you already own, so nothing gathers dust.
- “Which cocktails turn up in a film?”Search by movie or TV title and get the drinks featured in it, with a note on each scene.
- “Suggest a few drinks for six guests.”Build a varied menu across styles, or get one random pick when you can't decide.

Ask your assistant a question in plain language and it picks the right tool. Here are two real exchanges, end to end:

{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "find_cocktails_by_ingredient", "arguments": { "ingredient": "Campari" } } }

{ "count": 29, "cocktails": [ { "name": "Negroni", "family": "Spirit-Forward", "url": "https://cocktail.glass/negroni/" }, { "name": "Boulevardier", "family": "Spirit-Forward", "url": "https://cocktail.glass/boulevardier/" }, { "name": "Jungle Bird", "family": "Tiki", "url": "https://cocktail.glass/jungle-bird/" }, { "name": "Americano", "family": "Spritz", "url": "https://cocktail.glass/americano/" } ] }

Four of 29 matches shown. MCP delivers the list as the text content of a standard tool result.

Your assistant answers “You have 29 options with Campari. The classics are the Negroni and Boulevardier, or a Jungle Bird for something tiki.”

You ask “Which cocktails are in The Godfather?”

{ "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "find_cocktails_in_movie", "arguments": { "movie": "The Godfather" } } }

{ "count": 6, "appearances": [ { "name": "Godfather", "movie": "The Godfather", "year": 1972, "note": "A scotch and amaretto drink named for the film…" }, { "name": "Banana Daiquiri", "movie": "The Godfather Part II", "year": 1974, "note": "Fredo Corleone orders one at a Havana cafe…" }, { "name": "Godmother", "movie": "The Godfather Part III", "year": 1990, "note": "Vodka and amaretto, a nod to the films…" } ] }

Three of six appearances shown. The match runs over the scene description too, so a character, actor, or director — “Hemingway”, “Tarantino” — works as well as a title.

Your assistant answers “Six across the trilogy — Fredo's banana daiquiri in Part II is the famous one, and the Godfather and Godmother cocktails are named for the films themselves.”

Every result carries a real page URL, so the agent can link straight to the full recipe, with measures, steps, glassware, and garnish.

Not every client speaks MCP. The same catalogue is open over plain HTTP:

The entire catalogue as one JSON file. All 500 cocktails, with ingredients, measures, and preparation steps.

Request any page with anAccept: text/markdownheader and you get a clean Markdown rendering instead of HTML. It's far cheaper for an LLM to read.

A structured Markdown map of the whole site, following the llmstxt.org convention.

Agents running inside the browser get the same seven tools in-page throughnavigator.modelContext, with no connection step.

/.well-known/api-catalog·MCP server card

Everything here is read-only and free to use.Browse the recipes →

MCP connector providing comprehensive access to Kochava's mobile measurement and attribution platform for advertisers. Includes analytics, attribution, campaign management, tracker creation, fraud detection, and reporting capabilities.