
A straightforward connection to TheCocktailDB that gives you four tools: search by name, fetch by ID, get a random recipe, or filter by ingredient. Each response includes measurements, instructions, glassware, and garnish details. It's part of the Pipeworx gateway ecosystem, so you can either connect to just the cocktails endpoint or hook into their full 673+ data source collection. No authentication required since it uses TheCocktailDB's free tier. Useful if you're building anything food and beverage related, need recipe data for a chatbot, or just want your AI assistant to suggest drinks based on what's in your cabinet.
Cocktails MCP — TheCocktailDB API (free, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_cocktails | Search TheCocktailDB for cocktail recipes by name. Returns name, category, alcoholic/non-alcoholic classification, glassware, thumbnail, and ingredient list with measurements (no preparation instructions — use get_cocktail for those). |
get_cocktail | Get full cocktail recipe by ID. Returns ingredients with exact measurements, preparation steps, glassware type, and garnish. |
random_cocktail | Get a random cocktail recipe. Returns ingredients with measurements, instructions, glassware, and garnish details. |
cocktails_by_ingredient | List all TheCocktailDB cocktails that contain a specific ingredient (e.g., 'vodka', 'lime juice'). Returns cocktail id, name, and thumbnail only — use get_cocktail to retrieve full recipes. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"cocktails": {
"url": "https://gateway.pipeworx.io/cocktails/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/cocktails/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Cocktails data" })
The gateway picks the right tool and fills the arguments automatically.
MIT