Skip to main content
Glama

Server Details

Mobile app analytics for your agent, in plain words. Ask how your iOS and Android apps are doing: live activity from Apparent's SDK, App Store Connect, Google Play and RevenueCat reviews and sales, ads, and why a number moved. Every tool is read-only. Connect with a personal token (Authorization: Bearer apt_...) made on Apparent's Connect page under Your agents. 14 days free, plans from $10. Home: https://apparent.fyi?ref=glama

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 8 tools

Disambiguation3/5

The tools mostly have distinct intents, but app_topic overlaps substantially with ad_campaigns, timeline, and why_did_it_change by including ads, timeline, and why sections. Summary-style tools such as how_are_my_apps, app_story, today, and app_topic also require careful interpretation to select correctly.

Naming Consistency3/5

All names use snake_case, but the naming pattern is mixed: noun phrases (ad_campaigns, app_story, timeline), a verb phrase (list_apps), and question-style names (how_are_my_apps, why_did_it_change). The names are readable but not predictable as a set.

Tool Count5/5

Eight tools is well-scoped for an app analytics server, with each major workflow represented without obvious bloat. The count supports both broad overviews and focused investigations.

Completeness4/5

The surface covers app listing, daily status, period summaries, topic deep dives, ads, timelines, and change explanations. Some secondary analytics needs such as app-to-app comparisons or alert/export workflows are not represented, but core app analytics coverage is strong.

Available Tools

8 tools
ad_campaignsApple Ads and Google AdsA
Read-only
Inspect

Use for anything about paid ads: which Apple Ads and Google Ads campaigns ran when, what each spent (in the ad account's own currency and in US dollars), what it brought (Apple counts each download; Google's installs are what Google says), what each download cost, buyers and money when they can be tied to the ad, share of store downloads from ads, payback, changes made to campaigns, the search terms that brought the most, and up to two suggested next steps (never done for the person).

Inputs: app (required), period. Returns: ads, app, next, period

app_storyHow one app is doingB
Read-only
Inspect

One app's story for a period in plain words, its key numbers (with ad spend when ads ran), and its highlights (sales, best days, new countries, reviews, problems, ads starting and stopping).

Inputs: app (required), period, source.

app_topicOne part of an app's numbersB
Read-only
Inspect

One topic for one app: numbers (key numbers: downloads, people, new people, money, sales, who pays, rating); highlights (sales, best days, milestones, new countries, releases, reviews, new problems, ads starting and stopping); countries (downloads by country, iPhone and Android); sources (where people found the app: store sources, recorded install sources, money by source); buyers (who bought, how soon after installing, what they did first, where they came from); problems (crashes and errors the app caught, failures it reported, Google Play crash counts); versions (which version people use, per platform); visits (a few recent visits, step by step, with the Mixpanel session replay id when the app records one); events (what people did in the app); reviews (the newest reviews); ads (Apple Ads and Google Ads: when each campaign ran, what it spent, what it brought, cost each, buyers when known, changes, search terms, next steps); why (why a number moved: the days far from usual in the period, or one day or range explained, causes biggest first with how much each explains); timeline (what happened when, oldest first: ads starting and stopping, campaign changes, releases, days far from usual with their top cause, best days, milestones, bursts of reviews); journey (how far people get, step by step, and where they stop: from the store to the first open, then inside the app (the app's own steps: onboarding, sign-in, the main thing people do, buying, coming back) with the biggest drop and what the people who left there did last (for Apparent's own app: from apparent.fyi to the first alert)); features (which features people use: each one's share of the period's people, days each, people on a usual day, and which are loved, hidden gems (few use them, those who do keep coming back), tried and not kept, or hardly used); properties (people active in the period by what the app told us about them (plan, language…), at their latest value).

Inputs: app (required), topic (required), metric, period, +1 more.

how_are_my_appsHow are my apps doingA
Read-only
Inspect

Every live app's last 7 days in two plain sentences each: downloads, sales and money, people and whether they come back, and ads when they ran. Use first for a general 'how is it going'.

Inputs: no named parameters.

list_appsList the appsA
Read-only
Inspect

The apps Apparent knows, with their ids, stage (live or TestFlight), whether RevenueCat is connected and whether they have ads.

Inputs: no named parameters.

timelineWhat happened whenA
Read-only
Inspect

Use to see a period as one list, oldest first, before explaining a chart or a change: ads starting, already running and stopping (with what they spent and brought), changes made to campaigns, releases, days far from usual with their top cause, best days, milestones and bursts of reviews. Each day far from usual has a whyId; ask why_did_it_change with its date for the full breakdown.

Inputs: app (required), period, source. Returns: app, period, timeline

todayToday so farA
Read-only
Inspect

Use for 'how is it going right now / today': people so far against a usual day at this same hour (busier, on pace, quieter), new people, what they did, a spike in the last hour or a slow stretch, sales and money, ads running today, and why today is busier or quieter. Leave out app for every app together. date (a past day like 2026-10-19) shows that whole day the same way.

Inputs: app, date. Returns: now, date, live

why_did_it_changeWhy a number went up or downA
Read-only
Inspect

Use whenever someone asks why a number moved: a spike, a drop, a quiet or busy day ('why did downloads spike on Sep 21?'). Give date for one day, or period for a range like 2026-09-20..2026-09-28 (explained as a whole, then the days in it far from usual); a period like 30d lists the days far from usual in it, newest first; 'today' explains today so far against a usual day at this hour. Each cause says how much of the number it explains ('Apple Ads 83 of 147'), whether a store or ad network counted it or it's worked out ('about'), what nothing explains, how sure the whole answer is (sure, likely, guess), and at most one suggested next step. Built from the data alone.

Inputs: app (required), date, metric, period, +1 more. Returns: app, why, metric, period

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      9 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources