Cocktail Glass
Remote MCP server over a catalogue of 500 cocktail recipes.
An AI-readable cocktail database
cocktail.glass isn't only 500 recipes for people to read. The whole catalogue is built for machines too. Connect an AI agent over the Model Context Protocol, pull structured JSON, or read any page as Markdown. No API key, no sign-up, no rate limits.
Connect an AI agent over MCP
The fastest way in is the Model Context Protocol (MCP) server. It's a remote, stateless endpoint at https://cocktail.glass/mcp. Point any MCP client at it and six cocktail tools — plus a guided prompt — appear.
One click
Add to Cursor Add to VS Code
Claude Code
claude mcp add --transport http cocktail-glass https://cocktail.glass/mcp
Claude Desktop, or any MCP client
{
"mcpServers": {
"cocktail-glass": {
"url": "https://cocktail.glass/mcp"
}
}
}
That's it. No key to paste. The server exposes six read-only tools — search_cocktails, get_cocktail_recipe, find_cocktails_by_ingredient, find_cocktails_in_movie, find_makeable_cocktails, and random_cocktail — plus a cocktails_from_my_bar prompt.
What you can ask it
Six 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.
See it work
Ask your assistant a question in plain language and it picks the right tool. Here are two real exchanges, end to end:
You ask “What can I make with Campari?”
The agent calls a tool
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "find_cocktails_by_ingredient",
"arguments": { "ingredient": "Campari" }
}
}
cocktail.glass returns
{
"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.
More ways in
Not every client speaks MCP. The same catalogue is open over plain HTTP:
/cocktails.json
The entire catalogue as one JSON file. All 500 cocktails, with ingredients, measures, and preparation steps.
Markdown content negotiation
Request any page with an Accept: text/markdown header and you get a clean Markdown rendering instead of HTML. It's far cheaper for an LLM to read.
/llms.txt
A structured Markdown map of the whole site, following the llmstxt.org convention.
WebMCP
Agents running inside the browser get the same six tools in-page through navigator.modelContext, with no connection step.
/.well-known/api-catalog · MCP server card
Machine-readable discovery documents (RFC 9727 and SEP-2127) so agents and registries can find all of the above on their own.
Everything here is read-only and free to use. Browse the recipes →
相關伺服器
agimem
Hosted MCP server for persistent, shared AI agent memory
Weather API MCP Server
Provides current weather data and forecasts using the QWeather API.
402 Index
MCP server for 402 Index: discover 15,000+ paid API endpoints across L402, x402, and MPP
USDV Capital — Your Real Estate CFO
Real estate market intelligence, financial calculators, investment screening, and capital advisory for US investors. 86K+ locations, 23 tools.
CHAI pentest tool
Cyber Host Artificial Intelligence (C.H.A.I) is Autonomous penetration testing MCP (Model Context Protocol) server with an integrated AI decision engine, multi-provider LLM support, and an extensible plugin architecture.
AFL (Australian Football League)
Provides Australian Football League (AFL) data, including games, standings, and team information, from the Squiggle API.
NFT Log Analyser
AI-powered log analysis MCP server. Scans 500MB+ log files locally, analyses errors with Ollama + CrewAI agents, and automatically files structured GitHub Issues. 100% local — no logs leave your machine.
Phone Carrier Detector
Detects Chinese mobile phone carriers, including China Mobile, China Unicom, China Telecom, and virtual carriers.
CRA Compliance MCP
Cyber Resilience Act compliance checker — vulnerability handling, software bill of materials, CE marking requirements for digital products
Pace
Pace is the first MCP connector that brings wearable health data directly into Claude — no third-party dashboards, no manual exports, no extra apps. Most health apps lock your data behind their own UI. Pace breaks that wall: connect once, and Claude can analyze your sleep, activity, workouts, nutrition and recovery in natural language — with full visualizations inline.