Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Apptiller

REMOTE · MCP.APPTILLER.COM · 2 COMPONENTS

Grow App Store apps: ranks, listing, ads, revenue and AI answers. Sign in to read your own apps.

+3 this week 76 Trust /100

Last scanned (13 hours ago)

Scores higher than 65% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Marketing and SEO

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security81
Transport & Reachability100
Schema Quality & AI Usability62
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 11066 tokens (~187/item across 59 items; 59 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 50% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 59 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 60 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • Authorization
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1
    • Tool “campaigns” rewrote its description, which is the text the model reads security
  • 18 Nov 26 0
    • Tool “campaigns” rewrote its description, which is the text the model reads security
  • 17 Nov 26 0
    • New tool “campaigns” functional
    • New tool “mark_move” functional
  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1
    • Server version: 0.1.1 → 0.1.3 functional
    • New tool “apple_ads_search_terms” functional
  • 12 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “app_store_charts” rewrote its description, which is the text the model reads security
    • Tool “app_store_drafts” rewrote its description, which is the text the model reads security
    • Tool “app_store_funnel” rewrote its description, which is the text the model reads security
    • Tool “app_store_keywords” rewrote its description, which is the text the model reads security
    • Tool “app_store_listing” rewrote its description, which is the text the model reads security
    • Tool “app_store_reviews” rewrote its description, which is the text the model reads security
    • Tool “app_store_sales” rewrote its description, which is the text the model reads security
    • Tool “apple_ads_accounts” rewrote its description, which is the text the model reads security
    • Tool “apple_ads_performance” rewrote its description, which is the text the model reads security
    • Tool “apply_proposal” rewrote its description, which is the text the model reads security
    • Tool “apps” rewrote its description, which is the text the model reads security
    • Tool “attribution_performance” rewrote its description, which is the text the model reads security
    • Tool “attribution_setup” rewrote its description, which is the text the model reads security
    • Tool “briefing” rewrote its description, which is the text the model reads security
    • Tool “check_launch” rewrote its description, which is the text the model reads security
    • Tool “close_site_guide” rewrote its description, which is the text the model reads security
    • Tool “connect_account” rewrote its description, which is the text the model reads security
    • Tool “data_coverage” rewrote its description, which is the text the model reads security
    • Tool “dismiss_finding” rewrote its description, which is the text the model reads security
    • Tool “edit_launch” rewrote its description, which is the text the model reads security
    • Tool “launch_ai_answers” rewrote its description, which is the text the model reads security
    • Tool “launch_product” rewrote its description, which is the text the model reads security
    • Tool “list_connections” rewrote its description, which is the text the model reads security
    • Tool “list_domains” rewrote its description, which is the text the model reads security
    • Tool “list_launches” rewrote its description, which is the text the model reads security
    • Tool “meta_ad_accounts” rewrote its description, which is the text the model reads security
    • Tool “meta_diagnose” rewrote its description, which is the text the model reads security
    • Tool “meta_performance” rewrote its description, which is the text the model reads security
    • Tool “organic_todo” rewrote its description, which is the text the model reads security
    • Tool “reject_proposal” rewrote its description, which is the text the model reads security
    • Tool “revenuecat_chart” rewrote its description, which is the text the model reads security
    • Tool “revenuecat_chart_options” rewrote its description, which is the text the model reads security
    • Tool “revenuecat_overview” rewrote its description, which is the text the model reads security
    • Tool “revenuecat_projects” rewrote its description, which is the text the model reads security
    • Tool “revenuecat_revenue” rewrote its description, which is the text the model reads security
    • Tool “set_app_brief” rewrote its description, which is the text the model reads security
    • Tool “set_app_limits” rewrote its description, which is the text the model reads security
    • Tool “set_site_guides” rewrote its description, which is the text the model reads security
    • Tool “setup_suggestions” rewrote its description, which is the text the model reads security
    • Tool “site_guides” rewrote its description, which is the text the model reads security
    • Tool “undo_change” rewrote its description, which is the text the model reads security
    • Tool “verify_domain” rewrote its description, which is the text the model reads security
    • Tool “to_do” rewrote its description, which is the text the model reads security
    • Tool “ai_referrals” rewrote its description, which is the text the model reads security
    • Tool “ai_referrals_setup” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_collect” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_plan” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_report” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_run_now” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_set_questions” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_track” rewrote its description, which is the text the model reads security
    • Tool “ai_visibility_tracked” rewrote its description, which is the text the model reads security
    • Tool “app_brief” rewrote its description, which is the text the model reads security
    • Tool “app_map_sources” rewrote its description, which is the text the model reads security
    • Tool “app_ownership” rewrote its description, which is the text the model reads security
    • Tool “app_performance” rewrote its description, which is the text the model reads security
    • Tool “close_site_guide” is now declared destructive security
    • Tool “dismiss_finding” is now declared destructive security
    • Tool “launch_product” is now declared destructive security
    • Tool “reject_proposal” is now declared destructive security
    • Tool “set_site_guides” is now declared destructive security
    • Schema quality: 163 → 183 ▼ functional
  • 11 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ai_visibility_plan” rewrote its description, which is the text the model reads security
    • Tool “launch_ai_answers” rewrote its description, which is the text the model reads security
    • Tool “set_site_guides” rewrote its description, which is the text the model reads security
    • Tool “site_guides” rewrote its description, which is the text the model reads security
    • Schema quality: 142 → 163 ▼ functional
    • New tool “app_store_drafts” functional
    • New tool “app_store_charts” functional
    • New tool “app_store_keywords” functional
    • New tool “app_store_reviews” functional
    • New tool “organic_todo” functional
    • New tool “to_do” functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.apptiller.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=apptiller.com CN=WE1,O=Google Trust Services,C=US 19 Oct 2026 17 Jan 2027 ECDSA 256 ECDSA-SHA256 146c071f0d4efd9d13ba8fb815082431
SANs: apptiller.com, mcp.apptiller.com, *.mcp.apptiller.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.apptiller.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
apptiller.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="OAuth", resource_metadata="https://mcp.apptiller.com/.well-known/oauth-protected-resource/mcp", scope="mcp:read"

Bearer realm="OAuth", resource_metadata="https://mcp.apptiller.com/.well-known/oauth-protected-resource/mcp", scope="mcp:read"

Protected resource metadata

Document https://mcp.apptiller.com/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://mcp.apptiller.com/mcp
Authorisation server https://mcp.apptiller.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.apptiller.com/mcp Verified 200
http (plaintext) http://mcp.apptiller.com/mcp Inconclusive 405
MCP tools · 59 exposed · ~10,376 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ai_referrals ~110

Use this when the user asks how many visitors AI assistants sent to their website. Whether the app's website script is installed (status), and what it counted from AI assistants over the last days (UTC): visits per assistant, clicks to the App Store or Google Play after one, purchases the site reported, by day, and the pages people landed on. Google AI Mode and AI Overviews refer from google.com and aren't counted here.

NameTypeReqDescription
daysinteger––
projectstringyes–

No output schema declared.

No examples provided.

ai_referrals_setup ~139

Use this when the user wants to count visitors that AI assistants send to their website. Turns on counting of the people ChatGPT, Perplexity, Gemini, Copilot, Claude and other assistants send to an app's own website, and their clicks to the App Store or Google Play (tagged with an App Store campaign token per assistant) or a purchase the site reports. Returns the script tag to add to the site; calling it again keeps the same key. Domains default to the ones AI-answer tracking knows, else the project's website. Counts only, no cookies.

NameTypeReqDescription
domainsarray––
projectstringyes–

No output schema declared.

No examples provided.

ai_visibility_collect ~51

Use this after asking the questions again, to fetch the answers that are ready. Fetches every queued answer that is ready and scores it. Runs by itself every hour; running it fetches fresh answers sooner.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ai_visibility_plan ~74

Use this when the user asks how many apps, questions or runs their AI-answer tracking covers. The organization's AI-visibility allowance: how many products and questions it covers and how many runs a day, what is used, and how the answers run: daily or once a week on a few questions, depending on the account.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ai_visibility_report ~111

Use this when the user asks whether ChatGPT or Google's AI answers recommend their app, and who they name instead. How often ChatGPT, Google AI Mode and AI Overviews named the app for its questions, with a 95% range, its average position when named, which apps they named instead, and which sites they cited (including whether the app's own site or store listing was cited).

NameTypeReqDescription
by_questionboolean––
daysinteger––
projectstringyes–

No output schema declared.

No examples provided.

ai_visibility_run_now ~73

Use this when the user asks for fresh AI answers now instead of waiting for the daily run. Queues one extra round of a project's questions on its engines now, instead of waiting for the daily run (up to 150 questions × engines). Answers arrive within about an hour.

NameTypeReqDescription
projectstringyes–

No output schema declared.

No examples provided.

ai_visibility_set_questions ~112

Use this when the user wants to add or change the questions AI answers are checked for. Adds the questions people would ask an assistant when looking for an app like this one, e.g. "best app to track PCOS symptoms". They work best in a buyer's own words, mostly without the app's name. With replace, questions not in the list stop being asked (their history is kept).

NameTypeReqDescription
projectstringyes–
questionsarrayyes–
replaceboolean––

No output schema declared.

No examples provided.

ai_visibility_track ~237

Use this when the user wants to start tracking whether AI assistants recommend their app. Starts (or updates) tracking whether ChatGPT, Google AI Mode and Google AI Overviews recommend an app. Creates the project if it does not exist. Give every name the app goes by, its own domains, its App Store id or Play package, and the competitors to compare against.

NameTypeReqDescription
aliasesarrayyesNames the app goes by in answers, e.g. ["Damson", "Damson PCOS"].
app_store_idstring––
competitorsarray––
countrystring–Where the questions are asked from, e.g. US.
domainsarray–The app's own sites, e.g. ["damson.life"].
enginesarray––
languagestring–e.g. en
play_packagestring––
projectstringyesProject name or id, e.g. "Damson".
runs_per_dayinteger–How many times a day each question is asked on each engine (0 pauses the daily runs).

No output schema declared.

No examples provided.

ai_visibility_tracked ~48

Use this when the user asks which apps and questions are tracked in AI answers. Lists the apps tracked in AI answers, what Apptiller looks for in each, and their active questions.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

app_brief ~174

Use this when the user asks what goal, markets, constraints or limits Apptiller works from for an app. What Apptiller's agent works from for one app: the brief the user set (the goal, such as a target cost per paying subscriber or a ROAS, core countries, competitors, constraints such as "don't touch brand campaigns", and short facts), the limits it works inside (mode: watch only reports, ask proposes and waits for approval; the biggest step one change may take; the most a day's budget may grow; which levers it may use; campaigns it must never touch), its open plan items with their check dates, its last 14 journal entries and what past changes taught it on this app. Read-only.

NameTypeReqDescription
appstringyesApp name or id (from apps).

No output schema declared.

No examples provided.

app_map_sources ~280

Use this when the user wants to add an app to Apptiller or link an ad account, attribution app or RevenueCat project to it. Creates an app (with create) and maps connected accounts to it: Meta and Apple Ads ad accounts (spend), AdServices, AppsFlyer and Adjust apps (attribution), RevenueCat projects (revenue). Name an account by source_id or provider:external_id as this account lists them (e.g. meta:act_123, revenuecat:proj1a2b, adservices:com.example.app). For an ad account shared by several apps, set campaign_name_prefix so only that app's campaigns count. remove unmaps; history stays. Also looks the app up on the App Store (name, icon, developer) from its App Store id, bundle id, or a mapped AdServices or AppsFlyer app.

NameTypeReqDescription
addarray––
appstringyesApp name or id, e.g. "Damson".
app_store_idstring––
bundle_idstring–iOS bundle id; used to find the App Store listing when the App Store id is not known.
createboolean–Create the app if it does not exist.
play_packagestring––
removearray––

No output schema declared.

No examples provided.

app_ownership ~102

Use this when the user asks whether Apptiller sees an app as theirs, or how to prove it. Whether the app is proven to be this organization's, and by what: a connected App Store Connect key that sees the app, or a verified domain that the app's App Store listing (developer website) points to. When it isn't, says what would prove it.

NameTypeReqDescription
appstringyesApp name or id, e.g. "Damson".

No output schema declared.

No examples provided.

app_performance ~449

Use this when the user asks about one app's ad spend, installs, revenue, ROAS or cost per install across ad networks. One app's spend, installs, trials, revenue, ROAS and cost per install, per day and per network (with an 'all' total per day) or per campaign, joined from Apptiller's synced history. Every number names its source: spend from the ad platforms; installs from the attribution layer (Apptiller's AdServices lookup for Apple Ads, the MMP for other networks), falling back to what the network claims, then to the revenue tool's tags; revenue, and so ROAS, from the MMP from the first day it has revenue for the app (revenue from the installs it attributed, USD, by install day; zeros mean the network earned nothing), else from the revenue tool's acquisition tags, whose split then sits in revenue_elsewhere; new customers and trials from the revenue tool, whose customers with no acquisition tag form an 'untagged' row (unknown source, not organic). Apple's own counts from App Store Connect sit beside each day's total in the network breakdown: first-time downloads in installs_elsewhere and proceeds (after Apple's commission, net of refunds) in revenue_elsewhere, standing in only on days no other layer counts; appleads rows carry app_store_search, Apple's count of all App Store search downloads, organic and Apple Ads together. Meta web campaigns (aimed at leads, sales or traffic, not app installs) carry web_results: the sign-ups, purchases and purchase value Meta's pixel counted on the website, Meta's own claim; they have no installs, the MMP doesn't judge them, and Meta's purchase value is their revenue only where the revenue tool has none tagged to them. ROAS only where spend and revenue share a currency. Set per_day false for one row per network or campaign over the whole range.

NameTypeReqDescription
appstringyesApp name or id (from apps).
breakdownstring––
per_dayboolean––
sincestringyesFirst day (inclusive).
untilstringyesLast day (inclusive).

No output schema declared.

No examples provided.

app_store_charts ~217

Use this when the user asks where an app sits in the App Store top charts, or why it moved. App Store category chart positions for one app, per storefront: for each chart Apptiller reads (top free or top paid, and top grossing, in the app's category) the place on the latest day read (null: not in the list), that day, the best place of the last 30 days, the place a week before, and the rivals from its search terms that are in the same list. moves lists the app's moves of 5 places or more over the 30 days (into or out of the list too), newest first, each with what Apptiller saw happen that day or the day before (a listing edit, a release, an App Store draft created, a reply posted, a page published, a listing gained). Charts are read daily on a plan. Read-only: it reads no chart itself.

NameTypeReqDescription
appstringyesApp name or id (from apps).

No output schema declared.

No examples provided.

app_store_drafts ~236

Use this when the user asks about proposed App Store listing edits, featuring nominations, in-app events or custom product pages. App Store listing and featuring drafts for one app, as Apptiller proposed them. listing_edits: open proposals for the promotional text, subtitle, keyword field or description, and those applied or undone in the last 90 days, each with its field, locale, the text live now (as the daily App Store Connect read last saw it), the text it was drafted from, the proposed text, why, its status (proposed, failed, applied, undone), any error, the version it rides on, and whether it was pasted by hand. store_drafts: featuring nominations, in-app events and custom product pages with their drafted text and dates, status (proposed, created in App Store Connect, submitted to Apple, failed) and any error; with the signs of being featured (jumps in App Store browse impressions) and readiness numbers. Read-only: it drafts, applies, creates, submits or rejects nothing.

NameTypeReqDescription
appstringyesApp name or id (from apps).

No output schema declared.

No examples provided.

app_store_funnel ~333

Use this when the user asks where an app's downloads came from (search, browse, websites, other apps) or about impressions, page views and conversion. Apple's App Analytics for each app, from App Store Connect's analytics reports, organic and paid alike: App Store impressions and page views, first-time downloads and redownloads, the conversion rate, purchases with proceeds in USD, subscription events (trial and paid offer starts, conversions to paid, paid starts, renewals, voluntary and involuntary churn, refunds) and active subscriptions (trials, paid offers, paid plans, billing issues), per app by day, by where people found the app (App Store search, which includes Apple Ads, App Store browse, App referrer, Web referrer) or by country. Days are UTC; the last two or three are incomplete. Apple makes these reports only after an Admin asks once, which Apptiller asks nobody to do, so only apps whose reports someone started (for another tool) have them. Says nothing about which campaign brought a download.

NameTypeReqDescription
appstring–An Apptiller app (name or id from apps) or an App Store Apple ID. All apps when left out.
bystring–day: one row per app and day; source: per source type over the range; country: per territory over the range.
countrystring–Only this territory, as Apple names it in the reports (e.g. US).
sincestringyesFirst day (inclusive), UTC.
untilstringyesLast day (inclusive).

No output schema declared.

No examples provided.

app_store_keywords ~319

Use this when the user asks which App Store searches an app ranks for, or how its keyword ranks moved. App Store keyword ranks for one app, per storefront: the search terms Apptiller tracks and the candidate terms it found, each with its rank on the latest check (null: not in the first 100), the day of that check, the median rank of the last 7 days and of the 7 before and the change, up to 21 days of rank history, difficulty (from the ratings the top 10 hold, and the store's own 0-100 score when read), the app holding #1, relevance to the app and why (as judged by a model over several runs), the sources that suggested the term, Apple Ads numbers for the same search, and App Store autocomplete suggestions. rank_error says why the last rank check failed, and rank_held why the last run left a tracked term out for the plan. Per storefront, search_pulse sets App Store search impressions over the last complete week against the week before, with the tracked terms that moved the same way. Ranks are read once a day on a plan and once a week without one. Read-only: it finds, tracks or drops no terms, and runs no rank check.

NameTypeReqDescription
appstringyesApp name or id (from apps).
countrystring–Only this storefront, e.g. US. Every storefront when left out.
include_droppedboolean–Also list the terms that were dropped.

No output schema declared.

No examples provided.

app_store_listing ~180

Use this when the user asks what an app's App Store listing says or what changed in it. An app's App Store listing (name, icon, developer, version, genre, price, rating) and every change Apptiller has seen to it: name, icon, description, screenshots, version and release notes, price. Checked daily; set refresh to look it up now. Uses Apple's public lookup, so it needs only the App Store id or bundle id, no App Store Connect access.

NameTypeReqDescription
appstringyesApp name or id (from apps).
countrystring–Storefront, e.g. US (default: the one used before, else US).
daysinteger–How far back to list changes.
refreshboolean–Look the listing up now instead of showing the last daily check.

No output schema declared.

No examples provided.

app_store_reviews ~245

Use this when the user asks what reviewers say about an app, which reviews need an answer, or how its ratings are trending. App Store reviews for one app from App Store Connect: the last 60 days' reviews (up to 25, unanswered first, lowest rating first), each with its rating, title, text, storefront, date, theme and the theme's kind (bug, request, price, praise, other), whether it has an answer and its text, and any reply Apptiller drafted. unanswered counts every review of the 60 days without an answer, beyond the 25 listed. themes counts the last 90 days' reviews per theme with their average rating. ratings: the summary rating and count, new ratings in the last 28 days against the 28 before, downloads and new ratings per 1,000 downloads in each, per version, and advice when the pace fell. key says whether an App Store Connect key reads them. Reviews are read daily on a plan and once a week without one. Read-only: it drafts, sends or withdraws no reply.

NameTypeReqDescription
appstringyesApp name or id (from apps).

No output schema declared.

No examples provided.

app_store_sales ~254

Use this when the user asks about an app's downloads, sales, proceeds or refunds. Not for which ad brought a download. Apple's own daily App Store numbers from App Store Connect (Sales and Trends), organic and paid alike: first-time downloads, re-downloads, updates, in-app purchases, new and renewed subscriptions, refunds and the developer's proceeds (after Apple's commission and taxes, net of refunds, in the currency Apple pays for each storefront), per app by day, storefront country or product. Days are Pacific Time, Apple's report day; each day comes out the next morning and is synced within six hours. Says nothing about which ad brought a download.

NameTypeReqDescription
appstring–An Apptiller app (name or id from apps) or an App Store Apple ID. All apps when left out.
bystring–day: one row per app and day; country: per storefront over the range; product: per in-app purchase or subscription (and the app itself) over the range.
countrystring–Only this storefront, e.g. US.
sincestringyesFirst day (inclusive), Pacific Time.
untilstringyesLast day (inclusive).

No output schema declared.

No examples provided.

apple_ads_accounts ~78

Use this when the user asks which Apple Ads accounts Apptiller can read. Lists the Apple Ads ad accounts Apptiller can read, with the connected user's roles in each, straight from Apple. Accounts marked basic are Apple Ads Basic: Apple offers no reporting API for them, so there is no spend data and their results come through attribution.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

apple_ads_performance ~147

Use this when the user asks how their Apple Ads campaigns, ad groups or keywords are doing, as Apple reports them. Daily Apple Ads (App Store search ads) numbers from Apptiller's synced history: spend, impressions, taps, installs and every other metric Apple reports, by campaign, ad group, ad or keyword, between two dates. Synced four times a day; set raw to get Apple's full rows.

NameTypeReqDescription
campaign_idstring––
levelstring––
rawboolean––
sincestringyesFirst day (inclusive), in the ad account's reporting timezone.
untilstringyesLast day (inclusive).

No output schema declared.

No examples provided.

apple_ads_search_terms ~268

Use this when the user asks what people searched when their Apple Ads showed, which searches Search Match matched, or which searches to add as keywords or negatives. Apple's search terms report for one app's Apple Ads campaigns over the last 90 days (Apple's limit), read with each full sync: each search people typed, the campaign and ad group, whether Search Match found it (source AUTO) or one of the keywords did (source TARGETED, with the keyword and its match type), impressions, taps, installs and spend. to_add lists Search Match searches that brought installs and aren't a keyword yet (judged against every keyword the campaigns have, read from Apple, so one just added counts); no_installs lists searches with 5 taps or more and no install; waiting lists active keywords added in the last 14 days that have had no impression yet, with the day each was added; never_shown lists active keywords added longer ago with no impression in the history kept. Keywords are read once a day. Apple leaves out searches with fewer than 10 impressions. Read-only: it adds or blocks no keyword.

NameTypeReqDescription
appstringyesApp name or id, e.g. "Damson".
campaign_idstring––
limitinteger––

No output schema declared.

No examples provided.

apply_proposal ~202

Use this only after the user has seen a specific proposal and said to apply it. Not for changes the user describes without a proposal. Makes the change a proposal the user has seen and approved describes, in the live ad account: pauses the campaign, ad group or keyword, or moves its bid or daily budget by the proposed step (at most 20%). Apple Ads, Meta and Google Ads (Meta and Google Ads move budgets and pause; they have no bids to move). Apptiller first reads the entity live from the platform and writes only if it still has the value the proposal started from; the value it replaces is kept, so the change can be undone. A proposal waits while an earlier change to the same entity, one above it or one inside it is still being measured (7 days), so what each change did can be told apart. This spends or saves real money.

NameTypeReqDescription
proposal_idstringyesThe proposal id, from briefing.

No output schema declared.

No examples provided.

apps ~77

Use this when the user asks which apps are in their Apptiller account, or which accounts feed each app. Lists the apps in this Apptiller account with the ad accounts, attribution sources and revenue projects mapped to each (and which layer each one feeds), plus the connected accounts no app uses yet. Per-app performance covers mapped accounts only.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

attribution_performance ~172

Use this when the user asks which network, campaign or keyword brought installs, as the attribution tool counted them. Daily installs by attribution source from Apptiller's attribution layer (Apptiller's own Apple AdServices lookup, AppsFlyer and Adjust when connected: their rows carry every metric the MMP reports in metrics, including sessions, revenue, cost and in-app events; Adjust also has ad group rows), by network, campaign, ad group, keyword or ad, between two dates, with claim type, conversion type and country counts. These are installs as the attribution source saw them, not what the ad network claims or what the revenue tool tagged.

NameTypeReqDescription
levelstring––
sincestringyesFirst day (inclusive), UTC.
untilstringyesLast day (inclusive).

No output schema declared.

No examples provided.

attribution_setup ~163

Use this only when the user asks to set up Apple Ads attribution for an app that has no attribution or revenue SDK. An optional fallback for an app with no MMP (AppsFlyer, Adjust…) and no revenue SDK that collects Apple Ads attribution; Apptiller otherwise reads attribution from the tools already connected. Creates this organization's Apptiller ingest key and returns a Swift function to add to the iOS app. The app then sends each install's Apple AdServices token to Apptiller, which resolves it with Apple: which Apple Ads campaign, ad group, keyword and ad brought the install, for Advanced and Basic accounts alike, with no third-party SDK and no tracking prompt. Calling it again replaces the key; apps with the old key stop counting until updated.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

briefing ~571

Use this when the user asks what's wrong with their ads, what to change, or what an earlier ad change did. What Apptiller's analyst found in each app's last 14 days of synced data: Meta campaigns and ad sets, and Apple Ads campaigns, ad groups and keywords, that spent with no results, cost far more per result than the rest of their channel, or far less. Each finding has its evidence (spend, results and their source, cost per result with a 90% range, the baseline it was compared with), how sure it is, and one proposed change (pause, bid or budget). Like is compared with like: one channel, level, objective and currency, measured in the deepest result the group has enough of (purchases, trials, sign-ups, attributed installs, then installs the network claims), from one source. Also, per group, what it was judged by or why it couldn't be, and the changes Apptiller made in the app's ad accounts over the last 30 days (with change ids), each with its effect: the 7 days before it against the 7 after, in the result and source its finding was judged by, net of how the rest of its group moved over the same days, with how sure that is and a verdict (better, worse or unclear: cheaper results after a cut, more of them after a raise). An Apple Ads change also gets `search` once the app's App Store Connect analytics are connected (search results campaigns only): all of App Store search's first-time downloads a day before and after (Apple's App Analytics, organic included), the part Apple Ads credits its search results campaigns with, and the share of Apple Ads' move that was new to search, with a 90% range set by how much organic search moved week to week before (verdict incremental, organic or unclear, once Apple's numbers for all 7 days after are in); the analyst doesn't raise again what a raise mostly took from organic search. While a change is being measured, the analyst leaves alone the entity, those above it and those inside it; their proposals wait (status 'waiting', and `wa…

NameTypeReqDescription
appstring–App name or id (from apps). Every app when left out.
refreshboolean–Run the analysis now instead of showing the last daily run.

No output schema declared.

No examples provided.

campaigns ~349

Use this when the user asks what to do next for growth, how a campaign is going, or what a move brought. One app's growth brief (audiences, each with the posts and reviews its need rests on and the tracked question it is measured on; where what people say pulls against the listing; promise, objective, hours, the channels the founder does, whether it is confirmed, and the constraint read from its numbers, with the numbers) and each campaign: its audience, need, link token, and its moves (a page, a list, a link, a thread reply, a creator, a custom product page), each with its state (prepared, done, live as read back, dropped), what was prepared for it (the pitch or reply to send), where it can be seen, what the live read found, and its outcome (measuring, not enough data, blocked, activity seen, better or worse than before, can't tell, done) with why and the numbers it came from. Better is said only against a baseline; visits or citations alone are activity. The brief's plan is this week's work Apptiller chose within the founder's hours, with what it deferred and why, what past moves brought, and judged page changes to revise. site_issues are the technical problems the weekly site check found on the app's important pages (gone, failing, noindex, canonical elsewhere, text only after JavaScript, missing title, description or H1, broken links, missing from the sitemap), each with its fix. Moves and states are the same as the web app's Campaigns page.

NameTypeReqDescription
appstringyesApp name or id (from apps).

No output schema declared.

No examples provided.

check_launch ~66

Use this after the user connects or proves something that could change a launch's tier. Works out a launch's tier again from what is connected now (after connecting RevenueCat, mapping its project to the app, or proving ownership).

NameTypeReqDescription
launch_idstringyesFrom list_launches.

No output schema declared.

No examples provided.

close_site_guide ~88

Use this when the user says a guide went live, or wants to drop it. Marks one guide as published, with the full https address where it went live, so Apptiller counts its Google clicks from then on; or dismissed.

NameTypeReqDescription
guide_idstringyesThe guide id, from site_guides.
statusstringyes–
urlstring––

No output schema declared.

No examples provided.

connect_account ~98

Use this when the user wants to connect a service to Apptiller: App Store Connect, an ad account, an attribution tool, RevenueCat, Stripe or Google Search Console. Returns a one-time link (valid 15 minutes) that the user opens in a browser to connect a service to Apptiller. The user enters any keys or passwords on that page, not in the chat.

NameTypeReqDescription
providerstringyesThe service to connect.

No output schema declared.

No examples provided.

data_coverage ~157

Use this before judging ad campaigns by revenue or paying users, or when the user asks what their data can show. Per app and ad channel (Apple Ads, Meta, …), over the last 30 days of synced data: what Apptiller can judge the channel's campaigns by (paying subscribers, the MMP's purchase or trial event counts, Meta's own conversion counts, installs, or only the network's own claims), the source that rests on, and what is missing, with how to fix it in tools the user already has. Also each connected account's facts in its layer (installs, MMP revenue and purchase events, customers and tags, spend). Reads synced data only; asks nothing of the app.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dismiss_finding ~84

Use this when the user wants a finding to stop coming up. Dismisses one of the analyst's findings: it leaves the briefing, its pending proposal is rejected, and the analyst stays quiet about the same thing for 30 days. Nothing changes in the ad account, and changes already made stay.

NameTypeReqDescription
finding_idstringyesThe finding id, from briefing.

No output schema declared.

No examples provided.

edit_launch ~111

Use this when the user asks to change how a launch shows on the board. Changes what the board shows of a launch: its name, tagline, category, and whether dollar amounts are hidden (rank and growth still show). Fields left out stay as they are. The address (slug) never changes.

NameTypeReqDescription
categorystring––
hide_amountsboolean––
launch_idstringyesFrom list_launches.
namestring––
taglinestring––

No output schema declared.

No examples provided.

launch_ai_answers ~292

Use this when the user asks whether AI answers name their launched product. A claimed launch's free AI answers (tier owner or verified; an unclaimed launch can save questions but not run them): up to 5 questions someone who needs the product would ask (never naming it), asked on ChatGPT, Google AI Mode and AI Overviews. Pass questions to replace them; run: true starts the first check, once per launch (each question 3 times on every engine), asked as from country (US unless given). Claimed founding launches are then asked again every day until their period ends. Returns the questions and the results so far: how often the product is named and who is named instead, per question. With raw: true it also returns the latest day's answers themselves: each engine's text (up to 1500 characters), whether and where it named the product, who else it named, and the pages it cited. Answers arrive within a few hours.

NameTypeReqDescription
countrystring–With run: the country the answers are asked from, kept for the daily runs; usually where the maker's buyers are. Defaults to US.
launch_idstringyesFrom list_launches.
questionsarray––
rawboolean–Include the latest day's answers: text, names, cited pages.
runboolean–Start the first check (once per launch).

No output schema declared.

No examples provided.

launch_product ~260

Use this when the user asks to launch their app or website on Apptiller Launches. Launches an app (from its App Store link or id) or a website (its domain, plus a name) on Apptiller Launches, the public board ranked by the revenue a launch adds in its period, verified through the product's own RevenueCat app or its Stripe account and a TXT-verified domain (websites). It goes into the first open period with a spot (the founding month first). Returns the launch with its tier: verified (ranked), owner (ownership proven: listed, not ranked) or unverified, and what would raise it. One launch per product across Apptiller. Launching is free; it makes the product's name, tagline and launch-period numbers public.

NameTypeReqDescription
categorystringyes–
hide_amountsboolean–Show rank and growth only, never dollar amounts.
kindstringyes–
linkstringyesApp Store link or id for an app; domain or URL for a website.
namestring–Required for a website; an app's defaults to its App Store name.
taglinestringyesWhat it does, in one line.

No output schema declared.

No examples provided.

list_connections ~58

Use this when the user asks which services are connected to Apptiller. Shows which services (Meta Ads, App Store Connect, Apple Ads, Google Ads, RevenueCat, AppsFlyer, Adjust) are connected to this Apptiller account.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_domains ~53

Use this when the user asks which domains are verified. The organization's domains with their state (pending, verified, lapsed, failed) and the TXT record each one needs. Removing a domain is done in the web app.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_launches ~254

Use this when the user asks how their launches on Apptiller Launches are doing. This organization's launches on Apptiller Launches: period, tier, proof, what would raise the tier, the latest numbers (revenue added in the period so far, growth, new customers, trials), and the public page's traffic over the last 7 days (views by where they came from, clicks out to the product, badge loads on other sites). For an app, app_store_from_launches: the App Store page views and first-time downloads Apple's App Analytics credits to apptiller.com (Web referrer) since the launch was made (since, a UTC day as App Analytics counts them), through latest, the last day Apple's reports reached. latest null: Apple's Detailed reports haven't both come in (started false: App Analytics not started; started true: still coming in). latest before since: Apple hasn't reported the launch's days yet, so the zeros aren't counts. stopped: every App Store Connect key that reads the app is revoked or broken, so latest won't move until it's replaced. Apple leaves small counts out. Each has its page in the web app. Withdrawing is done in the web app.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mark_move ~154

Use this when the user says they did one of a campaign's moves (posted the reply, sent the pitch, put the page live, asked the creator) or want to drop one. done takes the day (YYYY-MM-DD, default today), where it can be seen (required for a page and a thread reply), and for a creator what was paid. Apptiller then reads it back and only marks it live once found. Nothing is sent or published by this tool.

NameTypeReqDescription
appstringyesApp name or id (from apps).
costnumber––
movestringyes–
onstring––
statestringyes–
urlstring––

No output schema declared.

No examples provided.

meta_ad_accounts ~41

Use this when the user asks which Meta ad accounts Apptiller can read. Lists the Meta ad accounts Apptiller can read, with currency and status.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

meta_diagnose ~58

Use this when Meta data is missing or a Meta account can't be read. Shows what the connected Meta token is (system user or person), its permissions and granted account ids, and what each ad-account lookup returns. Never shows the token.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

meta_performance ~175

Use this when the user asks how their Meta (Facebook, Instagram) ads are doing. Spend, impressions, reach, clicks, CPM, CTR and key results (purchases, trials, registrations, leads, installs, checkouts…) with cost per result and ROAS, for a Meta ad account by account, campaign, ad set or ad. Use a date preset such as last_7d, or since/until dates. Set raw to get Meta's full action list.

NameTypeReqDescription
account_idstringyesAd account id, e.g. act_123 (from meta_ad_accounts).
date_presetstring––
levelstring––
rawboolean–Return every Meta action type instead of the summary.
sincestring––
untilstring––

No output schema declared.

No examples provided.

organic_todo ~350

Use this when the user asks what to do to show up more in Google search or AI answers. One app's organic To do, as Search & AI › To do shows it: one ranked list of the work Google's searches and the AI answers point at, best first, each item in a group (New page: a need no page on the site answers, from Google searches, an AI question, or both; Improve a page: a page Google shows but few click, or just off the top results; Fix what AI says: a wrong claim, or rivals' App Store listings cited instead; Get listed or compared: a rival named instead, or a page the answers cite). Each item has its evidence lines from every source (Google impressions, clicks and position; the AI answers that leave the app out, by engine; the page that ranks now; its visits), its score and why it is first (Google clicks missed at a position a page can reach, plus AI answers weighted by engine, plus a draft waiting), its state (new, planned, drafted, or its guide ready, held, published or dismissed), its finding ids and its actions as the web app offers them. today says how the last morning run went: what it drafted, or why nothing, or the error. unavailable names any part that couldn't be read just now. done lists items marked done with what each brought: Google clicks on its page in the 28 days after against the 28 days before, and AI answers naming the app for its questions, saying where the 28 days aren't in yet.

NameTypeReqDescription
appstringyesApp name or id (from apps).
limitinteger––

No output schema declared.

No examples provided.

reject_proposal ~74

Use this when the user declines one of the analyst's proposals. Marks one of the analyst's proposals as rejected. Nothing changes in the ad account; the finding stays in the briefing, and the analyst doesn't propose that change again while the finding stays open.

NameTypeReqDescription
proposal_idstringyesThe proposal id, from briefing.

No output schema declared.

No examples provided.

revenuecat_chart ~197

Use this when the user asks how a subscription metric (trials, conversion, MRR, churn, retention) moved over time. A RevenueCat chart over time: trials, trial conversion, MRR, revenue, churn, actives, retention, refunds, paywall conversion and more, optionally segmented (e.g. by country or product) and filtered.

NameTypeReqDescription
chart_namestringyes–
currencystring––
end_datestring––
filtersarray––
limit_num_segmentsinteger––
project_idstringyesRevenueCat project id (from revenuecat_projects).
realtimeboolean––
resolutionstring–Resolution id from revenuecat_chart_options, e.g. "0" for day.
segmentstring–Segment id from revenuecat_chart_options.
selectorsobject––
start_datestring––

No output schema declared.

No examples provided.

revenuecat_chart_options ~77

Use this before building a RevenueCat chart, to see what it accepts. The resolutions, segments (country, product, store…), filters and selectors a RevenueCat chart accepts.

NameTypeReqDescription
chart_namestringyes–
project_idstringyesRevenueCat project id (from revenuecat_projects).
realtimeboolean––

No output schema declared.

No examples provided.

revenuecat_overview ~91

Use this when the user asks for an app's current subscription numbers, such as MRR, active subscriptions or trials. Current subscription metrics for a RevenueCat project: active trials, active subscriptions, MRR, revenue and new customers over the last 28 days, and active users.

NameTypeReqDescription
currencystring––
project_idstringyesRevenueCat project id (from revenuecat_projects).

No output schema declared.

No examples provided.

revenuecat_projects ~40

Use this when the user asks which RevenueCat projects Apptiller can read. Lists the RevenueCat projects Apptiller can read, with their ids.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Apptiller MCP server?

Apptiller is a hosted endpoint at https://mcp.apptiller.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.apptiller.com

# add to Claude Code
claude mcp add --transport http com-apptiller-apptiller 'https://mcp.apptiller.com/mcp'
Common questions

What is the Apptiller MCP server?

Apptiller is an MCP server listed in the public MCP registry as com.apptiller/apptiller. Grow App Store apps: ranks, listing, ads, revenue and AI answers. Sign in to read your own apps. This page covers its hosted endpoint (https://mcp.apptiller.com/mcp).

Is the Apptiller MCP server safe to use?

Apptiller scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Apptiller MCP server expose?

Apptiller exposes 59 tools: list_connections, setup_suggestions, connect_account, meta_ad_accounts, meta_diagnose, and 54 more. Their descriptions and schemas cost roughly 10,376 tokens of context every time the server is loaded.

Does the Apptiller MCP server require authentication?

Yes. Apptiller asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Apptiller MCP server still maintained?

Apptiller is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Apptiller MCP server?

VerifyMCP ran 12 checks on Apptiller, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Apptiller: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.