Skip to main content
Glama
chrischall

untappd-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Pick beers off a tap list that a user hasn't had

untappd_menu_pick

Converts raw beer menu lines into top-rated picks you haven't had yet. Resolves each line to an Untappd beer, checks your history, and ranks the unmatched beers by rating.

Instructions

One call from a tap list to "order this": give the raw menu lines as read from a photo and get back the top-rated beers the user has NOT had. It (1) refreshes the user's distinct-beers cache — an incremental refresh when the cache is complete, otherwise it backfills automatically within api_budget, no separate sync needed; (2) resolves each line to an Untappd beer (prices/punctuation stripped, scored on brewery + name match and check-in volume, venue_city as tie-breaker; resolutions are cached locally so repeat venues are instant); (3) treats " SEASONAL/ROTATING" as a list of possible beers (needs_confirmation) and "ROTATING CIDER"-style lines as unresolved ("ask bartender"); (4) checks every beer against the cache; (5) ranks the not-had ones by global rating. Returns picks, not_had, had, possible, unresolved, a sync block (what the refresh did) and freshness (coverage); if coverage is still incomplete a "not had" may be a false negative and another_run_needed is true. api_budget is also capped to the quota Untappd reports, when it reports one. Omit username for your own account.

Input Schema

NameRequiredDescriptionDefault
itemsYesRaw menu lines as read from the menu, e.g. ["JACKALOPE FENNARIO IPA $7", "BLACK ABBEY SEASONAL", "ROTATING CIDER"].
top_nNoHow many picks to return (default 2, max 10).
usernameNoUntappd username. Omit to use your own configured account (UNTAPPD_USERNAME).
api_budgetNoMax Untappd API calls this run, shared by the cache sync, searches and rating lookups (default 60; Untappd allows ~100/hour). If it runs out, the result says another_run_needed and a re-run continues from what was cached.
venue_cityNoCity of the venue (e.g. "Nashville") — breaks ties between same-named beers toward local breweries.
style_filterNoCase-insensitive substring filter on the beer style or parent style for the picks (e.g. "ipa", "stout").
refresh_resolutionsNoIgnore cached line→beer matches and re-search every line (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.4.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint=false and idempotentHint=false already declared, the description goes well beyond the annotations: it discloses the implicit cache write/backfill, api_budget consumption shared across sync/searches/lookups, the Untappd-reported quota cap, local resolution caching, and the false-negative risk when coverage is incomplete. That is exactly the mutation/rate-limit context an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause and the numbered pipeline makes the five stages easy to scan. It is dense and long for a description, with some load-bearing detail (quota cap, cache refresh semantics) buried inside the step list rather than split into its own sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with no output schema, the description enumerates the returned block (picks, not_had, had, possible, unresolved, sync, freshness) plus the another_run_needed signal, and explains how partial coverage produces false negatives. Nothing an agent needs to call it correctly or interpret the response is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description still adds meaning on top, notably that api_budget is also clamped to the quota Untappd reports, that venue_city acts as a same-name tie-breaker, and that omitting username targets the caller's own account. Items handling is deferred to the schema example, which is reasonable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource: takes raw menu lines transcribed from a photo and returns top-rated beers the user has NOT had. The input/output framing (

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear situational trigger (one call from a tap list to "order this") and explicitly says no separate sync step is needed, which preempts a likely wrong turn toward sync tools. It never names an alternative such as untappd_venue_pick or untappd_top_not_had, so there is no explicit when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools