Skip to main content
Glama
Sign In
untappd-mcp

untappd-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Get a venue's verified beer menu (section-paged)

untappd_venue_menu
Read-onlyIdempotent

Fetch a venue's full beer menu as a flat list by paging through every section, so multi-section menus are not under-reported. Resumable with an offset; cached 6 hours.

Instructions

Return a venue's verified beer menu as a flat, compact list of beers. untappd_venue_info returns only the FIRST section of each menu (Untappd defaults the section list to one), so it silently under-reports any venue whose menu spans multiple sections — e.g. a 23-beer wall that comes back with 2 items. This tool forwards the section_limit / section_offset paging params venue/info echoes back but never receives, walks sections up to a per-call max_pages budget (respecting the ~100 calls/hour limit — it does NOT loop to completion in one call), and flattens to [{bid, name, brewery, brewery_id, style, abv, price, serving_type, menu, section}]. Like the sync tools it is resumable: when the budget runs out before full coverage it returns another_run_needed:true plus next_section_offset to pass back on the next call. truncated:true means the upstream returned no more sections short of total_count (e.g. it ignored the paging params) — not resumable. Results are cached locally for 6 hours per venue + paging params (cache.hit, fetched_at, expires_at) so repeated trip planning does not re-spend calls; refresh:true re-fetches. With the cache, the result also carries favorite {is_favorite, sources, reason} for the venue, and favorite / brewery_favorite on each beer that is one (derived from username's history or added with untappd_favorite_add; default your account) — applied on read, so never stale. Get an id from untappd_search_venue. Read-only.

Input Schema

NameRequiredDescriptionDefault
sortNoMenu sort key (e.g. 'publish_order', 'highest_rated'). Optional.
menu_idNoRestrict to a single menu id (from a prior result). Optional.
refreshNoBypass the 6-hour local cache and call Untappd (default false)
usernameNoWhose favorites to mark (cache only; default your configured account)
venue_idYesUntappd venue id
max_pagesNoAPI calls to spend THIS run — page budget, not page size (default 3). Resume with next_section_offset if another_run_needed.
section_limitNoSections fetched per API call — page size (default 50).
section_offsetNoSection offset to start from; pass a prior next_section_offset to resume (default 0).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.6.1
    • addedInput schema / properties / refresh
      Added value: +{
+  "description": "Bypass the 6-hour local cache and call Untappd (default false)",
+  "type": "boolean"
+}
    • addedInput schema / properties / username
      Added value: +{
+  "description": "Whose favorites to mark (cache only; default your configured account)",
+  "minLength": 1,
+  "type": "string"
+}
  2. Changed1 schema field changedv2.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. Addedv1.8.1

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover read-only/open-world/idempotent, but the description adds substantial non-obvious behavior: a ~100 calls/hour limit, a per-call max_pages budget that deliberately does not loop to completion, resumability semantics, the distinction between another_run_needed (resumable) and truncated (upstream ignored paging), and a 6-hour cache with hit/fetched_at/expires_at. Slightly dense but genuinely informative beyond structured fields.

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

Conciseness3/5

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

It is front-loaded with the key differentiator, but the body is one long run-on paragraph of stacked parentheticals and em-dashes covering paging, truncation, caching and favorites. Each clause carries information, yet the density makes it harder to parse than a few short structured sentences would.

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 an 8-parameter, no-output-schema tool, the description covers the flattened beer record fields, the cache envelope fields, the favorite annotations applied on read, and both paging outcome flags. An agent has everything needed to call, resume, and interpret results.

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 per-field text already explains max_pages vs section_limit and refresh/username. The description still adds operational meaning the schema cannot: that these paging params are what venue/info echoes back but never receives, and that next_section_offset is the resume token to pass back.

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?

"Return a venue's verified beer menu as a flat, compact list of beers" names a specific verb, resource and output shape. It immediately contrasts itself with untappd_venue_info, so an agent can distinguish the two without reading either schema.

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

Usage Guidelines5/5

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

It states exactly when NOT to use the sibling (venue_info returns only the first section and silently under-reports) and names untappd_search_venue as the source of an id. It also gives the refresh:true condition for bypassing cache and the next_section_offset condition for resuming.

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