MCP App Store
by KeenEthics
V-Kit icon

V-Kit MCP Server for ChatGPT

By VALAS OÜ – podružnica v Sloveniji

Overview

V-Kit (Marketing Kit) answers questions about your own marketing numbers in plain words. Connect your accounts once on marketing-kit.app — Meta Ads, Facebook Pages, Instagram, TikTok Ads, Apple Ads, Google Ads, Google Analytics 4, Search Console, Google Play, AppsFlyer, RevenueCat and App Store Connect — and ask: spend and CPI by campaign, Apple Ads search terms and impression share, users and events, search queries and positions, Google Play installs, sales and reviews, installs by media source, MRR, trials and churn, downloads and proceeds, App Store ratings and reviews. V-Kit reads data only from the accounts you connect, with the permissions you grant; it does not change campaigns, budgets or ads. Every operation is a separate tool with its own input schema. Two actions write, and both show a dry run first and run only after your explicit confirmation in words that name the action and the object: copying AppsFlyer partner-integration settings, and turning on App Store Connect Analytics Reports. Large tables come back as a summary with CSV and JSON download links valid for 24 hours, available only to you. API keys for AppsFlyer, RevenueCat and App Store Connect are entered on marketing-kit.app/connections, never in the chat. Limitations: organic TikTok is not covered; data freshness follows each platform's API.

How to connect

  1. ChatGPT: Open the V-Kit listing in the ChatGPT app directory and choose Connect. ChatGPT listing V-Kit exposes 88 tools here.

Tools

mk_app_store_connect_accounts

ChatGPT
same as apps, in the shared accounts shape Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_app_store_connect_analytics

ChatGPT
App Store Analytics Reports of one app — funnel (impressions, page views, downloads, conversion), by source, sessions, installs/deletions, crashes, or any report by name; says so when analytics_enable has not been run for the app Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_app_store_connect_analytics_enable

ChatGPT
Enable Analytics Reports for an App Store app: creates an ONGOING Analytics Reports request in App Store Connect. Nothing user-visible changes (no app, version, price or review is touched); the request only starts the data flow. Call it with dry_run=true first (the default): it shows the app, the access type and the existing requests and creates nothing. Apply with dry_run=false and confirm=true only after the user's explicit yes in words naming the action and the object — never set confirm=true on your own. It needs App Store Connect access with the Admin role (a narrower role gets a 403 naming the role). If an active ONGOING request already exists nothing is created. The first reports appear in 1–2 days. Use when: the user asks to turn on Analytics Reports for an app, or mk_app_store_connect_analytics says enabled:false. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_app_store_connect_apps

ChatGPT
apps of the App Store Connect team (Apple id, name, bundle id, SKU, primary locale) Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_app_store_connect_experiments

ChatGPT
Product Page Optimization experiments with treatments and custom product pages of an app; the API gives no test results Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_app_store_connect_reference

ChatGPT
Reference data for App Store Connect: Sales and Trends columns, product type identifiers, subscription report columns and events, Analytics Reports names, data latency, rate limit and what the API does not provide. Use when: reading the output of mk_app_store_connect_sales, mk_app_store_connect_subscriptions or mk_app_store_connect_analytics. No network call. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_app_store_connect_reviews

ChatGPT
customer reviews of an app with developer responses, filtered by territory, rating, period and response; average rating and counts; read-only Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_app_store_connect_sales

ChatGPT
Apple's own Sales and Trends for a required period (up to 92 days daily, or monthly) — installs, redownloads, updates, in-app purchases, subscription units, refunds and proceeds per currency (never converted), by date/country/device/product/app/product type; reports are Pacific-time, D+1 Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_app_store_connect_subscriptions

ChatGPT
subscription reports for a required period (up to 92 days) — report=summary: active subscriptions, trials, billing retry and grace period by day (snapshot); report=events: Subscribe, trial starts and conversions, Cancel, Refund, Reactivate counts by event/date/country/subscription Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_app_store_connect_versions

ChatGPT
App Store versions of an app (state, release type and date) with optional localized texts, plus app infos (name, subtitle) Use when: Apple's official numbers for the user's own apps (downloads, proceeds, store funnel, reviews, versions). Another app's public data is mk_apple. Needs the user’s App Store Connect account connected on https://marketing-kit.app/connections (#app-store-connect).

mk_apple_ads_accounts

ChatGPT
Apple Ads ad accounts the grant covers — account_id, name, org, roles, currency, time zone, status Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer.

mk_apple_ads_adgroups

ChatGPT
ad groups of an ad account or campaign — status, pricing model, schedule Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_ads_ads

ChatGPT
ads of an ad account, campaign or ad group — creative, status Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_ads_campaigns

ChatGPT
campaigns of an ad account — status, app (promotedObjectId), daily budget, bid strategy, schedule Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_ads_impression_share

ChatGPT
impression share of an app by search term and country — share range, rank, search popularity; daily or weekly Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_ads_keywords

ChatGPT
keywords of a campaign or ad group — text, match type, bid, status Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_ads_negative_keywords

ChatGPT
negative keywords of a campaign (campaign and ad group level) or of an ad group — text, match type, status Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_ads_reference

ChatGPT
Reference data for Apple Ads reports: report levels with their split dimensions (group_by) and whether they need a campaign, granularity limits, metrics with descriptions, impression share fields and limits, and the Apple Ads API roles. Use when: choosing the level, granularity, group_by or metrics of mk_apple_ads_report, or reading impression share. No network call.

mk_apple_ads_report

ChatGPT
App Store performance report by campaigns / ad groups / keywords / search terms / ads — spend, impressions, taps, installs, CPT, CPI; total or daily / weekly / monthly, optional split by country, device, age or gender Use when: Apple Ads, the App Store search ads (spend, taps, installs by Apple's attribution, keywords, search terms, impression share). Store totals are mk_app_store_connect, attribution across networks mk_appsflyer. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_apple_charts

ChatGPT
top apps by country and chart type Use when: public App Store data of any app (rating, reviews, version, charts), also competitors. No sales or subscriptions.

mk_apple_lookup

ChatGPT
app metadata by ID (version, rating, release date) Use when: public App Store data of any app (rating, reviews, version, charts), also competitors. No sales or subscriptions.

mk_apple_reviews

ChatGPT
latest user reviews Use when: public App Store data of any app (rating, reviews, version, charts), also competitors. No sales or subscriptions.

mk_appsflyer_accounts

ChatGPT
the account's apps (app_id, platform, name) — App list API (dev.appsflyer.com/hc/reference/app-list-ad-nets-api-get). Use when: attribution — installs and in-app events by media source and campaign, duplicate purchases (app SDK vs RevenueCat S2S). Not subscription revenue (mk_revenuecat) or store totals (mk_app_store_connect). Needs the user’s AppsFlyer account connected on https://marketing-kit.app/connections (#appsflyer).

mk_appsflyer_aggregate

ChatGPT
aggregated Pull API reports (daily_report, partners_report, partners_by_date_report, geo_report, geo_by_date_report) — installs and in-app by media source/campaign/adset/geo; a period is required. Use when: attribution — installs and in-app events by media source and campaign, duplicate purchases (app SDK vs RevenueCat S2S). Not subscription revenue (mk_revenuecat) or store totals (mk_app_store_connect). Needs the user’s AppsFlyer account connected on https://marketing-kit.app/connections (#appsflyer). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_appsflyer_integration_copy

ChatGPT
Copy AppsFlyer partner-integration settings from one app to another for one platform. By default every call is a dry run (dry_run=true): it only shows what would change and writes nothing. A change is applied only with dry_run=false and confirm=true — and only after the user has seen the “before → after” and explicitly said yes in words naming the action and the object. Never set confirm=true on your own. Use when: the user asks to copy integration settings (reading AppsFlyer data is mk_appsflyer_aggregate and the other mk_appsflyer_* tools). Needs the user’s AppsFlyer account connected on https://marketing-kit.app/connections (#appsflyer).

mk_appsflyer_purchase_dedup

ChatGPT
purchase duplicates between the app (SDK) and server-to-server events (RevenueCat): raw in-app events for up to 31 days by Event Source and receipt validation, duplicate groups, signals and the recommended one-source-per-event scheme; counts only, no ids; needs the Raw Data module. Use when: attribution — installs and in-app events by media source and campaign, duplicate purchases (app SDK vs RevenueCat S2S). Not subscription revenue (mk_revenuecat) or store totals (mk_app_store_connect). Needs the user’s AppsFlyer account connected on https://marketing-kit.app/connections (#appsflyer).

mk_appsflyer_raw

ChatGPT
raw Pull API events row by row (installs_report, in_app_events_report, organic_installs_report, organic_in_app_events_report) — only with the Raw Data module in the plan; personal data (device IDs, customer user IDs, IPs) is never returned. Use when: attribution — installs and in-app events by media source and campaign, duplicate purchases (app SDK vs RevenueCat S2S). Not subscription revenue (mk_revenuecat) or store totals (mk_app_store_connect). Needs the user’s AppsFlyer account connected on https://marketing-kit.app/connections (#appsflyer). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_appsflyer_reference

ChatGPT
Reference data for AppsFlyer: the names of the aggregate and raw (in-app events, installs…) reports, example raw columns, what the purchase duplicate check returns, and notes on the Raw Data module. Use when: choosing the report for mk_appsflyer_aggregate or mk_appsflyer_raw. No network call. Needs the user’s AppsFlyer account connected on https://marketing-kit.app/connections (#appsflyer).

mk_fb_pages_accounts

ChatGPT
Facebook Pages the user manages — id, name, category, followers, tasks (page tokens are never returned) Use when: organic numbers of a Facebook Page (reach, posts, engagement, followers). Not paid ads.

mk_fb_pages_page_insights

ChatGPT
page metrics per day for a period (reach, content views, engagements, followers); periods over 90 days are split Use when: organic numbers of a Facebook Page (reach, posts, engagement, followers). Not paid ads. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_fb_pages_post_insights

ChatGPT
insights for 1–25 posts of a page (reach, content views, clicks, reactions by type) Use when: organic numbers of a Facebook Page (reach, posts, engagement, followers). Not paid ads. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_fb_pages_posts

ChatGPT
published posts of a page for a period with reaction, comment and share counts Use when: organic numbers of a Facebook Page (reach, posts, engagement, followers). Not paid ads. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_fb_pages_reference

ChatGPT
Reference data for Facebook Pages: live page and post metrics with their periods, the post fields, the deprecated metrics with replacements, and limits (100+ followers, 90 days per request). Use when: choosing metrics for mk_fb_pages_page_insights or mk_fb_pages_post_insights, or when Meta says a metric is invalid. No network call.

mk_feedback_get

ChatGPT
One of the user's notes to the V-Kit developer with its whole thread: the text, kind, status, attachments and every reply (author developer or user, text, on), plus add_screenshot_url to attach a picture. id — from mk_feedback_list, or feedback_id from feedback_reply. Use when: the user asks to see one note in full — "show that one". Not for data questions.

mk_feedback_list

ChatGPT
The user's own notes to the V-Kit developer, newest first, at most 50: id, sent_on, kind, channel, excerpt, replies, last (author, on), status (needs_answer, answered, delivered). since/until (YYYY-MM-DD; until includes the whole day) when the user names a time — work out the dates for "last week" and say them. Relay dates, kinds, excerpts and whether the developer replied; empty — say so, invent nothing. Use when: the user asks what they sent — "what did I write (on <date> / last week)?". Not for data questions.

mk_feedback_mute

ChatGPT
Record that the user asked not to be asked for feedback for a while: no note is sent, nothing else changes. mute_days — how many days (1–30) the periodic question (feedback_invite) stays off; the answer holds muted_until. Use when: the user says "don't ask again" or similar after a feedback invitation; confirm briefly and offer no more in this chat. Not for sending a note.

mk_feedback_reply

ChatGPT
Send the user's answer to the V-Kit developer's reply (the reply came as feedback_reply in a tool result). reply_to — feedback_id from feedback_reply, or the note's id from mk_feedback_list. text — only the user's own words, in their language: their answer is the consent; never invent, complete or summarise a reply for them, no data from their accounts. At most 20 notes and answers a day (too_many_feedback). Use when: the user answers the developer's reply that came as feedback_reply. Not for data questions.

mk_feedback_send

ChatGPT
Send a note from the user to the V-Kit developer: a bug, something missing or an idea. Call it only after the user said yes and saw the text you will send. text — what the user tried to do, what went wrong and their own words, in the user's language; never put numbers, campaign names or rows from their accounts in it unless the user asks. kind — bug, idea or other. context — for a failed request, the context from feedback_invite (tool, mode, error_code, error_message); for a call that never reached the server, tool, mode and what happened (e.g. error_message "blocked by the client before reaching the server"). screenshot — {data: base64, mime} only if you have the image bytes; otherwise send the text and give the user add_screenshot_url from the answer to attach the picture there. At most 20 notes a day (too_many_feedback). Use when: a tool answer had feedback_invite and the user agreed; you offered it because a V-Kit call did not reach the server or returned nothing, the user said something does not work or a goal failed after 2 attempts, and the user agreed; or the user asks to tell the developer something. Not for data questions.

mk_ga4_accounts

ChatGPT
the source's available accounts Use when: behavior on the site or in the app after the click (events, sessions, funnels). Not search queries (mk_search_console) or ad spend.

mk_ga4_metadata

ChatGPT
the property's available dimensions and metrics (getMetadata), including registered custom customEvent:/customUser: ones — check them before report/realtime when using non-public field names. Use when: behavior on the site or in the app after the click (events, sessions, funnels). Not search queries (mk_search_console) or ad spend.

mk_ga4_realtime

ChatGPT
runRealtimeReport for the last ~30 minutes, with its own (Realtime) quota separate from Core reports. Use when: behavior on the site or in the app after the click (events, sessions, funnels). Not search queries (mk_search_console) or ad spend. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_ga4_report

ChatGPT
regular (Core) runReport report — dimensions/metrics/filters/orderBys, a period is required, offset/limit with auto-pagination for large volumes, returnPropertyQuota; the response flags sampling and thresholds. Use when: behavior on the site or in the app after the click (events, sessions, funnels). Not search queries (mk_search_console) or ad spend. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_google_ads_accounts

ChatGPT
accessible customer_ids (customers:listAccessibleCustomers) Use when: paid Google ads (spend, campaigns, conversion actions). Organic search is mk_search_console. Google Ads: the manager account (MCC) is detected automatically — the user does not enter anything; mk_google_ads_accounts lists every account, direct or via a manager account. A login customer ID saved on https://marketing-kit.app/connections (#google_ads, Advanced) overrides the detection and is needed only to pick one specific manager account.

mk_google_ads_objects

ChatGPT
reference lists: campaigns / ad_groups / ads / conversion_actions Use when: paid Google ads (spend, campaigns, conversion actions). Organic search is mk_search_console. Google Ads: the manager account (MCC) is detected automatically — the user does not enter anything; mk_google_ads_accounts lists every account, direct or via a manager account. A login customer ID saved on https://marketing-kit.app/connections (#google_ads, Advanced) overrides the detection and is needed only to pick one specific manager account. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_google_ads_reference

ChatGPT
Live GAQL field metadata from Google (googleAdsFields): for each field its category, data type, whether it can be selected, filtered or sorted, which fields it can be selected with, and enum values. Pass names (exact field names, e.g. metrics.cost_micros) or name_like (a substring, e.g. cost); one of the two is required. Use when: before a GAQL query in mk_google_ads_report — to check that field names exist and can be combined. Do not guess field names. Google Ads: the manager account (MCC) is detected automatically — the user does not enter anything; mk_google_ads_accounts lists every account, direct or via a manager account. A login customer ID saved on https://marketing-kit.app/connections (#google_ads, Advanced) overrides the detection and is needed only to pick one specific manager account.

mk_google_ads_report

ChatGPT
arbitrary GAQL report via googleAds:search; a period and LIMIT are required Use when: paid Google ads (spend, campaigns, conversion actions). Organic search is mk_search_console. Google Ads: the manager account (MCC) is detected automatically — the user does not enter anything; mk_google_ads_accounts lists every account, direct or via a manager account. A login customer ID saved on https://marketing-kit.app/connections (#google_ads, Advanced) overrides the detection and is needed only to pick one specific manager account. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_google_play_apps

ChatGPT
apps of the Google Play developer account (package name, title) from the Play Developer Reporting API Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_earnings

ChatGPT
the monthly earnings report (charges, Google fees, taxes, refunds per transaction), totals per merchant currency and transaction type, never converted Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_installs

ChatGPT
installs, uninstalls and upgrades by day from the monthly Play Console statistics files, by one dimension (country, device, app version, OS version, carrier, language) plus daily totals; data is 3 to 7 days late Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_reference

ChatGPT
Reference data for Google Play Console: report files and columns (installs, sales, earnings, subscriptions), install dimensions, vitals metrics and dimensions, required Play Console permissions, data delays and limits. Use when: choosing the dimension, metrics or period for a mk_google_play_* tool, or reading its output columns. No network call.

mk_google_play_refunds

ChatGPT
voided purchases (refunds and chargebacks) of the last 30 days with order id, time, source and reason Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_reviews

ChatGPT
reviews of the last 7 days from the Google Play Developer API (rating, text, device, developer reply, paging, translation), or a whole month from the reports bucket with month Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_sales

ChatGPT
estimated sales per order from the monthly Play Console report (buyer-currency amounts before Google fees), totals per currency and financial status, never converted Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_subscriptions

ChatGPT
new, canceled and active subscription counts per product, base plan, offer and country; counts only, no revenue Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_google_play_vitals

ChatGPT
Android vitals from the Play Developer Reporting API — crash and ANR rates by day or hour with dimensions (version, device, country, API level), end clamped to the latest data Use when: Google's official numbers for the user's own Android apps in Google Play Console (installs, ratings, sales, earnings, subscriptions, reviews, refunds, crashes/ANR). Another app's public data is not available.

mk_instagram_account_insights

ChatGPT
account metrics for a period (reach, views, engaged accounts, interactions, follows); windows of up to 30 days, optional breakdown and daily series Use when: organic numbers of an Instagram professional account (reach, posts, reels, followers). Instagram ads are in mk_meta. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_instagram_accounts

ChatGPT
Instagram professional accounts linked to the user's Facebook Pages — username, followers, media count Use when: organic numbers of an Instagram professional account (reach, posts, reels, followers). Instagram ads are in mk_meta.

mk_instagram_media

ChatGPT
posts, reels and carousels of an account published in a period with likes and comments counts Use when: organic numbers of an Instagram professional account (reach, posts, reels, followers). Instagram ads are in mk_meta. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_instagram_media_insights

ChatGPT
insights for 1–25 media items (reach, views, saves, shares, interactions); unsupported metrics per media type are reported in errors Use when: organic numbers of an Instagram professional account (reach, posts, reels, followers). Instagram ads are in mk_meta. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_instagram_reference

ChatGPT
Reference data for Instagram insights: live account and media metrics with metric types and breakdowns, the media fields, the deprecated metrics with replacements, and data delays and limits. Use when: choosing metrics for mk_instagram_account_insights or mk_instagram_media_insights, or when Meta says a metric is invalid. No network call.

mk_meta_accounts

ChatGPT
the source's available accounts Use when: paid Facebook/Instagram ads (spend, CPI, campaigns, ads). Not organic Instagram or Page numbers.

mk_meta_conversions

ChatGPT
custom conversions of the ad account (cached, not fetched on every report) Use when: paid Facebook/Instagram ads (spend, CPI, campaigns, ads). Not organic Instagram or Page numbers.

mk_meta_events

ChatGPT
event counts for a period with no source breakdown — actions from insights + pixel stats Use when: paid Facebook/Instagram ads (spend, CPI, campaigns, ads). Not organic Instagram or Page numbers.

mk_meta_insights

ChatGPT
performance report (spend, impressions, clicks, actions...), level/breakdowns/attribution windows, synchronous or as an async report Use when: paid Facebook/Instagram ads (spend, CPI, campaigns, ads). Not organic Instagram or Page numbers. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_meta_objects

ChatGPT
campaigns/adsets/ads — status, objective, budgets (in minor units), targeting Use when: paid Facebook/Instagram ads (spend, CPI, campaigns, ads). Not organic Instagram or Page numbers. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_meta_reference

ChatGPT
Reference data for Meta Ads insights: the standard insights fields (spend, impressions, clicks, actions…) and the breakdowns (publisher_platform, country, age, gender…) with a note on combinations. Use when: choosing the fields or breakdowns of mk_meta_insights. No network call.

mk_revenuecat_accounts

ChatGPT
same as projects, in the shared accounts shape Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_chart

ChatGPT
a RevenueCat chart for a required period (mrr, revenue, actives, trials, churn, conversion_to_paying, trial_conversion, ltv, refunds, cohorts…) by day/week/month with segments and filters; rows date × measure × segment Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_revenuecat_chart_options

ChatGPT
segments, filters, resolutions and selectors available for one chart Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_customer

ChatGPT
one customer by app user id — active entitlements, subscriptions (status, renewal, period, revenue) and purchases; personal data is not returned Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_entitlements

ChatGPT
entitlements of the project with their products Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_offerings

ChatGPT
offerings and packages (which products the paywall shows), the current offering Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_overview

ChatGPT
key subscription metrics now — MRR, active subscriptions, active trials, revenue, new customers and active users of the last 28 days Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_products

ChatGPT
products of the project (store identifier, type, duration, trial) Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat). Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_revenuecat_projects

ChatGPT
RevenueCat projects of the connection with their apps (App Store, Play, Stripe…) Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_reference

ChatGPT
Reference data for RevenueCat: the list of charts with descriptions, overview metrics, resolutions, currencies, revenue types, subscription statuses, rate limits and notes. Segments and filters of one chart are in mk_revenuecat_chart_options. Use when: choosing the chart, resolution or currency for mk_revenuecat_chart. No network call. Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_revenuecat_revenue

ChatGPT
total revenue of the project for a required period — gross, net of taxes or proceeds Use when: subscription money — MRR, trials, churn, LTV, one customer's subscriptions. Not ad campaigns (mk_appsflyer). Needs the user’s RevenueCat account connected on https://marketing-kit.app/connections (#revenuecat).

mk_search_console_accounts

ChatGPT
same as sites, in the shared accounts shape Use when: organic Google Search before the click (queries, impressions, position, indexing). Behavior after the click is mk_ga4.

mk_search_console_inspect

ChatGPT
URL Inspection — Google index status of one URL (verdict, coverage, canonical, last crawl) Use when: organic Google Search before the click (queries, impressions, position, indexing). Behavior after the click is mk_ga4.

mk_search_console_reference

ChatGPT
Reference data for Search Console: metrics, dimensions, search types, filter operators and the data limits (delay, retention, row limits, time zone). Use when: choosing dimensions, search type or filters for mk_search_console_report. No network call.

mk_search_console_report

ChatGPT
Search Analytics — clicks, impressions, CTR and average position for a required period by date/query/page/country/device (search type web, image, video, news, discover, googleNews; filters; up to 50 000 rows, paged by 25 000); totals with impression-weighted position Use when: organic Google Search before the click (queries, impressions, position, indexing). Behavior after the click is mk_ga4. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_search_console_sitemaps

ChatGPT
submitted sitemaps with errors, warnings, last download and submitted URL counts Use when: organic Google Search before the click (queries, impressions, position, indexing). Behavior after the click is mk_ga4. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_search_console_sites

ChatGPT
Search Console properties of the Google account (URL-prefix and sc-domain) with the permission level Use when: organic Google Search before the click (queries, impressions, position, indexing). Behavior after the click is mk_ga4.

mk_status

ChatGPT
Handshake with the V-Kit server: the server version, who is signed in (with the time zone), which sources are connected (meta, fb_pages, instagram, tiktok, apple_ads, google_ads, ga4, search_console, google_play, appsflyer, revenuecat, app_store_connect, apple) and the state of the sources' APIs (the api block). A source with reauthorize: true or missing_scopes needs that account reconnected on https://marketing-kit.app/connections; the other sources work. clients — the account's clients (named groups of connected sources: slug, name, sources) and clients_max; with several clients the sources block is for the client named in the client argument, without it the answer has client_required: true instead. plan.state — whether access to the sources is open; next_step — what to tell the user first (when access is closed, it is the message to relay as is). Use when: at the start of every session, before any other mk_* tool, and to check why a source does not answer. One optional argument: client.

mk_tiktok_accounts

ChatGPT
advertisers authorized for the connection — advertiser_id, name, currency, timezone, status Use when: TikTok ads (spend, impressions, clicks, conversions). Organic TikTok is not available.

mk_tiktok_objects

ChatGPT
campaigns / ad groups / ads of an advertiser — status, objective, budget Use when: TikTok ads (spend, impressions, clicks, conversions). Organic TikTok is not available. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

mk_tiktok_reference

ChatGPT
Reference data for TikTok Ads reports: report levels (advertiser, campaign, adgroup, ad) with their ids and name metrics, dimensions, metrics with descriptions, the default metrics, and notes. Use when: choosing the level, dimensions or metrics of mk_tiktok_report. No network call.

mk_tiktok_report

ChatGPT
ad performance report (spend, impressions, clicks, conversions...) by advertiser/campaign/ad group/ad, optional daily split; long periods are split into 30-day windows automatically Use when: TikTok ads (spend, impressions, clicks, conversions). Organic TikTok is not available. Large tables (over 200 rows, over 50 KB, or with save: true) come back as a summary (columns, totals, first 20 rows) and download links to CSV and JSON on marketing-kit.app, valid 24 hours, for the signed-in user only.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/v-kit"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/v-kit)