percolate-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SUPABASE_URL | No | Override the database URL | |
| SUPABASE_SERVICE_ROLE_KEY | No | Internal use only — unlocks live 30-day collection-add trending. Never distribute this key. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_coffeesA | Search 1,100+ curated specialty coffees in the Percolate database. Filter by category (espresso, single_origin, blend, decaf, dark), roast level, brew method, and price (USD). Returns tasting profiles, brew methods, and where-to-buy links. |
| get_coffeeA | Detailed record for one coffee: roast level, body/acidity/sweetness profile, flavor notes, suited brew methods, food and brew pairings, price, and retailer links. Accepts a Percolate id or a name. |
| find_similarA | Coffees with a similar profile to a given one, ranked by shared flavor notes and roast/body/acidity/sweetness proximity. Deterministic scoring over Percolate's structured tasting data. |
| get_recommendationsA | Personalized coffee picks from flavor preferences (e.g. 'chocolate', 'berry', 'caramel'), a budget in USD, roast preference, and the brew gear you own. |
| compare_coffeesA | Side-by-side comparison: roast, body/acidity/sweetness, shared and distinct flavors, brew methods, and price difference. |
| trending_coffeesA | Coffees Percolate users are adding to their collections most over the last 30 days (falls back to catalog popularity when live activity data is unavailable). The method used is labeled in the response. |
| dial_in_suggestionA | Brew guidance for a specific coffee: curated recipes from the Percolate catalog (ratio, temperature, grind) when available, or a roast-based starting point. Optionally scoped to your brew method. |
| what_to_brewA | A coffee suggestion for right now, based on time of day (evening picks lean decaf), mood, and the brew method you're using — scored over Percolate's tasting profiles. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools are distinct, but what_to_brew, get_recommendations, find_similar, and trending_coffees all exist to surface coffee suggestions with different inputs. An agent looking for 'a recommendation' could plausibly select the wrong one if it doesn't carefully parse the trigger context.
The majority of tools follow a clean verb_noun snake_case pattern like search_coffees, get_coffee, and compare_coffees. Minor deviations such as what_to_brew and trending_coffees break the pattern slightly, but the overall naming remains predictable and readable.
Eight tools are well-scoped for a specialty coffee discovery and brewing guidance domain. Each tool serves a clearly useful purpose, and the count feels complete without being bloated or thin.
The server covers the full coffee exploration journey: search, detailed lookup, comparison, similar coffees, personalized recommendations, trending picks, and dial-in brewing advice. Minor gaps exist around explicit catalog facets or lightweight list/browse operations, but agents can work around those with search filters.