Mağaza MCP
You can manage both App Store Connect and Google Play from one MCP server, including cross-store comparisons and full API access.
List and inspect apps, versions, TestFlight builds, reviews, subscriptions, IAP products, sales reports, and Play release channels/crash metrics.
Compare the same app’s subscriptions and prices across both stores in one call, including country-specific pricing.
Diagnose “paid but no premium” issues by checking product availability, pricing, subscription status, and Play purchase tokens.
Reply to App Store and Google Play reviews, update store text/listings, set subscription or IAP prices, configure subscriptions, age ratings, retention messages, and upload/release Play builds.
Scan an Apple developer account for termination/removal risk and fix supported findings with approval.
Search and call the full App Store Connect and Google Play API catalog, and inspect request-body schemas.
Protect write actions with explicit
onayla=trueapproval; read-only mode removes most write-capable tools.
Provides tools for interacting with App Store Connect, including listing apps, subscriptions, in-app purchases, TestFlight builds, App Store versions, customer reviews, sales reports, and updating store metadata or developer review responses.
Provides tools for interacting with Google Play, including listing apps, subscriptions, one-time products, release channels, crash rates, user reviews, validating purchase tokens, checking refunds, and responding to reviews.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Mağaza MCP Nota Defteri aboneliği App Store'da ve Play'de Türkiye'de kaç para?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mağaza MCP
App Store Connect and Google Play, in one MCP server. Let your AI assistant manage both stores.
You don't type anything into a terminal to install this. Drop this line on your AI assistant, it handles the rest:
https://github.com/tunaarikaya/magaza-mcp — install this, read AGENTS.mdYou: How much is Nota Defteri's monthly subscription on App Store vs. Play in Turkey?
Assistant: ₺129.99 on the App Store, ₺99.99 on Play. Play is noticeably cheaper — if you want the same price in both stores, you need to update the base plan on Play.
No other MCP server can answer that in a single call, because they all look at
one store. magaza-mcp sees both at once.
No server sits in the middle: the package runs on your own machine, talks directly to Apple and Google, and your keys never leave your Keychain.
📚 Table of contents
The difference from single-store servers | |
Have your assistant do it — you don't type commands | |
If you're not using an assistant | |
No — here's why | |
Example prompts | |
Is your Apple account at risk? | |
Full list of all 41 tools | |
1,440 operations, ~9,000 tokens | |
What Apple and Google require | |
Keys, approval gates, telemetry | |
Common errors |
Related MCP server: mcp-appstore-connect
🎯 Why this exists
Almost every MCP server on the market covers a single store. If you want both, you install two separate servers, juggle two separate tool sets, and manually stitch together any question that needs a comparison.
Question | With single-store servers | With |
"How much is this subscription in both stores?" | Two separate queries, manual comparison | One call, side by side |
"User paid but didn't get premium, what's wrong?" | You figure out which store first | Scans both at once, ranks findings |
"Where is what published?" | Two lists, manual matching | One list with iOS/Android pairs already matched |
The real win isn't more tools: it's tools that can query both stores in the same call, which is only possible once both are in one server.
⚡ Setup
Tell your assistant (Claude Code, Antigravity, Cursor, Codex, Gemini CLI…):
https://github.com/tunaarikaya/magaza-mcp — install this, read AGENTS.mdThe assistant reads AGENTS.md and handles the entire setup. All you do is answer its questions:
You › https://github.com/tunaarikaya/magaza-mcp — install this, read AGENTS.md
Assistant › Looking for your keys on this machine...
Found two keys:
App Store : ~/Downloads/AuthKey_ABC123DEFG.p8 (Key ID ABC123DEFG)
Play : ~/.config/play/account.json (publish@project.iam...)
Want me to use these? If there's another file, tell me the path,
or copy the key and paste it — either works.
You › yes, use them
Assistant › I need the Issuer ID for App Store. It's the UUID above the key
list on App Store Connect → Users and Access → Integrations.
You › 69a6de70-0000-0000-0000-000000000000
Assistant › ✓ App Store Connect connected — 4 apps found
✓ Google Play connected — 3 apps found
✓ Registered in Claude Code and Antigravity settings
Restart Claude Code, then ask:
"List my apps across both stores"If it can't find your key, it will ask you how to proceed: give it the file path, copy the key to your clipboard, or — if you don't have a key yet — it'll walk you through getting one step by step.
The assistant never sees the contents of your key. It runs the setup,
but the commands take the file's path, read its contents themselves, and
write it straight into the Keychain. Even when you paste the key via
clipboard (pbpaste | …), the content flows through a pipe and never enters
the assistant's context. AGENTS.md tells the assistant this explicitly.
After setup, restart any open applications — MCP servers only load at startup.
Client | Config file |
Claude Code |
|
Claude Desktop |
|
Antigravity (IDE + CLI) |
|
Cursor |
|
Windsurf |
|
Codex |
|
Your existing config is left untouched — only the magaza-mcp entry is
added or updated, a .magaza-mcp-yedek backup is taken before every write,
and the write itself is atomic.
🧑💻 Manual setup
If you're not using an assistant, a wizard does the same job:
npx magaza-mcp kur Mağaza MCP setup
App Store Connect + Google Play, in one setup
1. Which stores should we connect?
App Store Connect (iOS / macOS)? [Y/n] y
Google Play (Android)? [Y/n] y
2. App Store Connect key
Key ID: ABC123DEFG
Issuer ID: 00000000-0000-0000-0000-000000000000
Path to .p8 file: ~/Downloads/AuthKey_ABC123DEFG.p8
Connecting to Apple... ✓ 4 apps found
✓ Key saved (macOS Keychain)
3. Google Play service account
Path to service account JSON: ~/.config/play/account.json
Connecting to Google... ✓ 3 apps found
✓ Key saved (macOS Keychain)
4. Which clients should it be installed to?
Claude Code? [Y/n] y
Antigravity (IDE + CLI)? [Y/n] y
Cursor? [y/N] n
Setup complete.# | Question | Note |
1 | Which stores? | App Store, Play, or both |
2 | App Store key | Key ID, Issuer ID, |
3 | Play service account | Path to the JSON key — also verified against Google |
4 | Which clients? | Clients detected on your machine come pre-checked |
5 | Read-only? | No by default |
Keys are never written to the config file. On macOS they're saved to the
Keychain; the config file only gets which stores are enabled (MAGAZALAR).
On systems without Keychain access, it falls back to a file with 0600
permissions.
npx magaza-mcp tara # Search the machine for .p8 and service account keys
npx magaza-mcp anahtar ... # Verify a key and write it to the vault (below)
npx magaza-mcp kaydet # Register the server in clients' configs
npx magaza-mcp durum # Show what's connected (--json for machine-readable)
npx magaza-mcp araclar # List installed tools (✎ = can modify data)
npx magaza-mcp kur # Manual setup wizard
npx magaza-mcp surum # Print version
npx magaza-mcp yardim # HelpRegistering a key (the command-line equivalent of the wizard's Q&A step):
npx magaza-mcp anahtar --apple-p8 ~/Downloads/AuthKey_ABC123DEFG.p8 \
--issuer-id 69a6de70-0000-0000-0000-000000000000
npx magaza-mcp anahtar --play-json ~/.config/play/account.json
pbpaste | npx magaza-mcp anahtar --play-json - # from clipboard, no file
npx magaza-mcp anahtar --sil appstore # remove from the vaultIf --key-id isn't given, it's read from the filename. A key is never
written to the vault without being verified against Apple/Google with a real
request; if verification fails, the existing key in the vault is left
untouched.
🧩 Do the two stores mix up?
No — and that's not an accident, it's the design itself.
1. Tool names are separated by prefix. Every tool going to App Store
starts with appstore__, every tool going to Play starts with play__. A
tool never talks to both APIs. There's no shared name, so there's nothing to
mix up.
2. Tools for the store you didn't pick are never loaded. On startup, the
server reads the MAGAZALAR variable and builds the tool list from it — the
other store's tools aren't even loaded into memory, aren't shown to the
model, and cost zero tokens.
Setup | Tools loaded |
Both stores | 41 |
App Store only | 22 |
Play only | 19 |
Read-only (both stores) | 27 |
3. Cross-store tools only exist when both stores are enabled. In a single-store setup they're never created at all — they'd have no meaning.
4. The dispatch tools know their scope too. The magaza parameter on
magaza__endpoint_ara and magaza__cagir is an enum that only accepts the
stores you've set up. If you only installed Play, the model can't make a call
with magaza: "appstore" — the schema doesn't allow it.
💬 What you can ask
The app names in the examples are made up; you'd use your own app's name.
Both stores at once
"List my apps across both stores — where's each one published?"
"What's Nota Defteri's monthly subscription on App Store vs. Play in Turkey? Is there a difference?"
"A user says they paid but didn't get premium. Check the purchase setup in both stores."
App Store
"Which of my versions is stuck in review?"
"Did yesterday's TestFlight build finish processing?"
"Summarize the 1- and 2-star reviews from the last week — what's the most common complaint?"
"Update the 'What's New' text for the version in preparation."
Google Play
"Which version is on the production channel and what percentage of users does it reach?"
"Has the crash rate gone up over the last 14 days?"
"Is this purchase token valid, is the subscription still active?"
"Draft a polite reply to this review, but show me first."
🚨 Account health
Apple terminates developer accounts every year for spam, copycat apps and review manipulation — and many developers find out only when the email arrives. Most of them never knew they were doing anything wrong: the same screenshots in five apps, "Instagram" in the keywords, someone else's copyright left over from a template.
appstore__hesap_sagligi scans the whole account and scores the risk from
0 to 100:
You › Is my developer account safe?
Assistant › ACCOUNT RISK: 72/100 🔴 HIGH
Clones / spam (4.3) ██████████ critical (3)
Metadata & trademarks (2.3/5.2) █████░░░░░ high (4)
Reviews & money (5.6/3.1) ██░░░░░░░░ low (2)
Review history & account ██████░░░░ medium (3)
1. [CRITICAL] Same screenshots in 6 apps
2. [HIGH] Photo Pro: "instagram" in the keywords
3. [HIGH] 3 apps carry someone else's copyright
…Section | What it looks for |
Clones / spam | Identical screenshots across apps, near-identical names and descriptions, |
Metadata & trademarks | Brand names (Apple, Instagram, ChatGPT…) in names and keywords, "best / #1 / free" in the name, keyword stuffing, Android mentions, missing privacy or support URL, media downloaders, fake-function apps |
Reviews & money | Scam / refund complaints, 5-star bursts, copy-paste reviews, misleading review replies, refund rate, apps with no downloads, overpriced weekly subscriptions, rejected IAPs |
Review history & account | Rejections, reviews stuck for days, apps Apple removed, apps not updated in 3+ years, EU trader status, missing declarations (content rights, encryption, demo account, review notes, age rating), too many admins |
Every finding comes with the Apple guideline, why it's risky and the steps to fix it.
Parameter | What it does |
| Scan a single app (Apple id, bundle ID or name). Clone detection needs the whole account. |
| Only these sections: |
| All languages and 1,000 reviews per app (slower). Default: primary language + en-US, 200 reviews |
| Vendor number — adds the refund rate and 12-month download checks |
Fixing. Findings marked automatic can be fixed with
appstore__hesap_duzelt. It always shows the change first and only writes
with onayla=true:
appstore__hesap_duzelt(bulgular: ["anahtar-marka:1234567:en-US"])
→ preview: keywords "photo,instagram,edit" → "photo,edit"
appstore__hesap_duzelt(bulgular: ["anahtar-marka:1234567:en-US"], onayla: true)
→ appliedFindings that need a value (privacy URL, copyright, demo account) take it
through degerler. If there's no editable version, it tells you instead of
creating one. Heavy moves — pulling an app from sale, demoting an admin —
are only explained, never done.
Quiet fixes. The advice never pushes you to knock on Apple's door: issues are fixed on your side, ideally in your next regular update; reporting reviews, messaging App Review unprompted or volunteering explanations is not recommended. If Apple asks, answer briefly and honestly. Every finding comes with a "don't" list — the reflexes that draw attention.
What it can't see. The API doesn't expose Apple's internal flags, rejection reasons or Resolution Center messages, or links to other accounts (same device, card or freelancer — the most common unexplained termination). So the tool reports risk signals, not a verdict, and says what it couldn't check.
Ask things like:
"Is my developer account safe?"
"Why is my review taking so long?"
"Fix the keyword problems you found, but show me first."
🧰 Tools
The prefix tells you which store a tool goes to. Tools marked ✎ modify
data and won't run without onayla=true.
These tools only load when both stores are connected.
Tool | What it does |
| Collects apps from both stores into one list; puts the iOS/Android pair of the same product side by side, and separates out apps that only exist in one store. |
| Compares the same app's subscriptions across both stores: product IDs, durations, and prices in the requested country. Converts the country code to whichever format each store expects. |
| Diagnoses "paid but no premium" issues: are the products live, do they have a price in that country, is the plan open to new subscribers; if you give it a Play purchase token it verifies that too, and writes up its findings as a list. |
Tool | What it does |
| Lists the apps on the account: name, bundle ID, SKU, primary language, and the |
| Shows an app's App Store versions and their status (in preparation, in review, live, rejected). |
| Lists TestFlight builds, their processing status, and expiry dates. |
| Fetches customer reviews, newest first; filterable by rating and country, or only the ones without a reply yet. Shows the existing developer response if there is one. |
| Writes a developer response to a review (published after Apple's moderation). |
| Lists subscription groups and the subscriptions in them: product ID, duration, status. |
| Fetches a subscription's customer price and developer proceeds, country by country. |
| Lists one-time in-app purchase products. |
| Shows TestFlight beta groups, how many testers are in each, public invite links, and quotas. |
| Updates the store text of the version in preparation: release notes, description, keywords, promotional text. |
| Downloads the sales/download report as TSV: daily, weekly, monthly, or yearly; sales, pre-order, installs, subscriptions, subscription events, subscribers, and offer code reports. |
| Fetches Apple's App Review Guidelines live on every call — never a baked-in copy, so it can't go stale. With no query, reports which rule numbers changed since the last check (local diff cache). With a query (a rule number or a keyword), returns the current full text of matching rules, for reviewing an app's code against. |
| Sets a subscription's price in every country at once: give one price (e.g. USA 9.99), Apple's equalization table fills in all ~175 countries and they're written in a single request. Add country-specific prices on top ( |
| Regional pricing suggestion, writes nothing: starts from Apple's equalized price and applies a softened discount based on each country's purchasing power (World Bank). Never raises a price, never cuts more than half, leaves rich countries alone. The output plugs straight into |
| Sets a one-time purchase's price from a single base country; Apple fills in the rest. |
| Makes a subscription available in every country (or the ones you list) in one request. |
| Creates a subscription from scratch behind one approval: group → subscription → localized names → availability → prices in all countries. |
| Sets up a retention message shown when a subscriber starts to cancel: message → version → localized header/body → assigned to the subscription(s), behind one approval. Images/offers are optional add-ons via |
| Reads or fills in the age rating questionnaire (Apple's 2025 questions). Finds the editable app info by itself; only the answers you give change. |
| Scans the whole developer account for termination, removal and long-review risk: a 0–100 score, findings tied to Apple guidelines, why each one is risky and how to fix it. See Account health. |
| Fixes findings from |
Tool | What it does |
| Lists the apps the service account can access; this is where you get the package name other tools need. |
| Shows release channels (internal, alpha, beta, production) and the versions on each, with user rollout percentages. Requires the service account to have release-management permission. |
| Fetches user reviews, translating them if asked. The Play API only returns roughly the last week. |
| Writes a developer response to a review (350 characters max). |
| Lists subscriptions and their base plans: duration, status, number of priced countries. Includes archived ones if asked. |
| Fetches a base plan's prices country by country, and whether it's open to new subscribers; also checks the "rest of world" fallback price for countries not listed individually. |
| Lists one-time products; tries both the new ( |
| Verifies a purchase token: subscription status, acknowledgment status, expiry date, whether it's a test purchase. |
| Lists cancelled, refunded, or charged-back purchases; turns the refund reason and source into something readable. Google only returns the last 30 days. |
| Android vitals: crash and ANR rates (including the user-perceived rates Play uses for its bad-behavior thresholds), whether a threshold is exceeded, and the most frequent crash clusters with stack traces. Can be narrowed to one version code. |
| Uploads an AAB/APK and releases it to a track in one approval: upload → assign to track → release notes → commit. Give a percentage for a staged rollout (e.g. production 10%). If anything fails, nothing is committed. |
| Manages a track: change the rollout %, halt, resume, complete, promote a release to another track (internal → production), or update only the release notes. The preview shows the track before and after. |
| Reads or updates store listing text (title, short and full description, video) for every language in one edit. |
| Uploads screenshots, the icon, or the feature graphic, optionally replacing the existing ones. |
| Sets a base plan's price in every country at once from a USD price (Google's own conversion), with optional country-specific prices on top, or changes only the countries you list. |
| Regional pricing suggestion for Play, writes nothing: same purchasing-power logic as the App Store version, rounded to natural-looking local prices. |
Tool | What it does |
| Searches for an endpoint across all connected stores' APIs; returns the operation name, HTTP method, path, and parameters. |
| Runs the operation you found. Fills in path parameters automatically; operations that modify data won't run without |
| Shows what an operation's request body should look like; used before POST/PATCH calls. |
magaza__cagir is marked ✎ here because it can also run operations that
modify data. In npx magaza-mcp araclar output it doesn't show ✎ though:
since it's also the single gateway to every read endpoint in the catalog, it
isn't dropped from the list in read-only mode — only write operations through
it are blocked.
🌐 Full API access
The curated tools cover most day-to-day work. For everything else, the server carries the entire API surface of both stores:
Source | Operations |
App Store Connect API v4.5 | 1,270 |
Android Publisher API v3 | 145 |
Play Developer Reporting API v1beta1 | 25 |
Total | 1,440 |
When the curated tools aren't enough, the model first finds the operation it
needs with magaza__endpoint_ara, then runs it with magaza__cagir.
Why aren't they all separate tools?
MCP tool definitions get loaded into context on every request — the installed tool list is paid for again on every message, even if you don't use any of them.
Tools | Paid on every message | |
magaza-mcp | 41 | ~9,000 tokens |
If all were separate tools | 1,440 | ~210,000 tokens |
Nothing is locked away: all 1,440 operations are reachable, but the ones you don't use cost nothing. There's no "should I turn this feature on, it costs tokens" setting either — there's nothing to turn on.
The catalogs are generated from Apple's and Google's official
specifications: Apple's published App Store Connect OpenAPI file, and
Google's Android Publisher and Play Developer Reporting discovery documents.
There's no hand-written endpoint list. The 159 operations Apple marks as
deprecated aren't dropped from the catalog — some of them are the only way to
reach that capability — but their summaries start with [ESKİMİŞ]
(deprecated) and are pushed down in search results.
🔑 Required permissions
App Store Connect — The App Manager role is enough when creating the key; Admin isn't required. Exceptions: user/access management endpoints and some analytics reports need higher privileges.
Google Play — Both steps are required:
The service account must be invited from Play Console → Users and permissions and granted access to the relevant apps.
The Android Publisher API and Play Developer Reporting API must be enabled on the Cloud project. App listing and crash metrics come from the Reporting API, so the second one is genuinely required too.
Contract, tax, and banking informationcannot be read with any API key. Apple never exposes this data to the API at all; only the Account Holder can see it in the dashboard.
🔒 Security
Keys live in the Keychain. The Apple
.p8and Google service account JSON are stored in the macOS Keychain; never written to config files, environment variables, or the repo.The assistant never sees the key, even when it runs the setup. The
anahtarcommand takes the file's path, reads the content itself, and writes it straight to the vault; a key given via clipboard also flows through a pipe. The key's content never appears in any command's output —durumonly prints the last four characters of the Key ID,taraonly prints file paths.Operations that modify data require approval. Write tools don't run on the first call: they return what would happen and the expected request body; the operation only runs once the user approves and it's called again with
onayla=true. This is enforced server-side — it doesn't depend on the client's approval UI.Read-only mode.
--salt-okunur(orSALT_OKUNUR=1) removes every write-capable tool from the list entirely: the model can't see them or call them. 41 tools become 27.magaza__cagirstays in the list because it's also the single gateway for read endpoints in the catalog — but it refuses write operations when read-only mode is on.Path parameters are validated. IDs passed to tools are encoded before entering a URL; path-traversal attempts like
.and..are rejected. For absolute URLs the target host is validated, so no request can carry a token to anywhere other than Apple or Google.Clients can see which tools modify data. The tool list ships with MCP
annotations(readOnlyHint,destructiveHint).Package provenance is verifiable. Every version published to npm is built inside GitHub Actions, and npm generates a Sigstore-signed provenance attestation: the Provenance section on the npm page shows which commit in this repo the tarball you downloaded was built from. No publish token is stored in the repo; GitHub issues a short-lived, signed identity on every release (trusted publishing), so there's no publish key to steal either.
No telemetry. No analytics, error reports, or usage data are sent. Network traffic only goes to
api.appstoreconnect.apple.com,androidpublisher.googleapis.com,playdeveloperreporting.googleapis.com, andoauth2.googleapis.comfor tokens. The one exception is the twofiyat_analizitools, which read public purchasing-power figures fromapi.worldbank.org(no key, nothing of yours is sent). There's no server in the middle; data flows directly between your machine and Apple/Google.
🩺 Troubleshooting
The Key ID, Issuer ID, and .p8 file might not belong together — all three
need to be from the same key. If they match, check the system clock: the
signed JWT lives 20 minutes, and a token produced on a machine with a drifted
clock gets rejected by Apple. Also make sure the .p8 file is an App Store
Connect API key — StoreKit or push keys don't work here.
The key's role isn't sufficient for that operation. App Manager covers most things; user management and some reports need more.
Worth knowing upfront: contract, tax, and banking information can't be read with any API key. A 403 here isn't a misconfiguration, it can't be fixed.
The app has moved to Google's new product model; the legacy inappproducts
endpoint is now closed and oneTimeProducts should be used instead. The
play__urunler tool handles this itself: it tries the new endpoint first,
falls back to the legacy one if needed, and tells you in the output which
model it used.
The service account may not have been invited to the app in Play Console. After inviting it, permissions can take a few minutes to propagate. If the invite is already in place, verify that Android Publisher API and Play Developer Reporting API are enabled on the Cloud project.
Because the Android Publisher API has no app-listing endpoint — Google
never published one. Since no Publisher call can be made without knowing the
package name, the list is pulled from the Play Developer Reporting API's
apps:search endpoint instead. That's why the Reporting API needs to be
enabled not just for crash metrics, but for basic usage too.
On Play, channel information can only be read from within an "edit session." The read tools open this session themselves, read from it, and leave it without committing — so it creates no changes — but it does mean two extra HTTP calls.
🛠 Development
git clone https://github.com/tunaarikaya/magaza-mcp.git
cd magaza-mcp
npm install
npm run build # Compile TypeScript
npm run kontrol # Type-check (tsc --noEmit)
npm run dev # Compile in watch modeTo regenerate the tool catalogs from the specs:
node scripts/uret-katalog.mjsThis reads the three spec files under spec/ and rewrites the catalogs under
src/katalog/. The operation list is never hand-edited.
🤝 Similar projects
There are good projects in this space that came before this one. If your needs are limited to a single store, we genuinely recommend looking at them:
Heimdall — Covers the entire App Store Connect API with 890 tools, with a profile system that lets you narrow the tool set down. The deepest project in this space if you're only interested in iOS.
app-store-connect-mcp-server — The first one. Established the idea of putting App Store Connect behind an MCP server; everyone who came after owes something to it.
google-play-developer-mcp — A comprehensive, mature server on the Play side. More than enough if you're only publishing on Android.
Our difference: all of these look at a single store. magaza-mcp combines
both in one setup and offers tools that can compare both stores in the same
call — exactly what a single-store server can't do.
📄 License
MIT — see LICENSE for details. See THIRD-PARTY-NOTICES.md for third-party sources.
App Store, TestFlight, App Store Connect, Google Play, and Play Console are trademarks of their respective owners. This is an independent open-source project; it is not affiliated with, endorsed, sponsored, or supported by Apple Inc. or Google LLC.
Available Tools
27 toolsappstore__abonelik_fiyatlariARead-only
Bir aboneliğin ülke ülke fiyatlarını getirir. 'Bu abonelik Türkiye'de kaça' türü sorular için.
Inputs: abonelik_id (required), ulke, limit.
appstore__aboneliklerBRead-only
Bir uygulamanın abonelik gruplarını ve içlerindeki abonelikleri listeler. Ürün kimliği (productId), süre ve durum bilgisi döner.
Inputs: uygulama_id (required).
appstore__buildlerARead-only
TestFlight build'lerini listeler; işlenme durumunu ve son kullanma tarihini gösterir. En yeni build en üstte gelir. 'Yüklediğim build hazır mı' sorusunun cevabı.
Inputs: limit, uygulama_id.
appstore__iap_urunlerARead-only
Uygulamanın tek seferlik uygulama içi satın alma ürünlerini listeler (abonelik olmayanlar).
Inputs: uygulama_id (required), limit.
appstore__metin_guncelleADestructive
Bir sürümün mağaza metinlerini günceller: sürüm notları, açıklama, anahtar kelimeler, tanıtım metni. Yayındaki sürüm düzenlenemez, sadece hazırlanmakta olan sürüm düzenlenebilir.
Inputs: yerellestirme_id (required), onayla, aciklama, surum_notlari, +2 more.
appstore__satis_raporuARead-only
Satış ve indirme raporunu indirir (TSV biçiminde). Günlük, haftalık, aylık veya yıllık olabilir. Apple raporları 1-2 gün gecikmeli yayınlar ve hiç satış olmayan gün için dosya üretmez. Not: SUBSCRIBER raporu yalnızca DETAILED alt türüyle çalışır; abonelik raporları çoğu zaman bir sürüm numarası ister (örn. 1_3).
Inputs: tarih (required), satici_no (required), tur, surum, +3 more.
appstore__surumlerARead-only
Bir uygulamanın App Store sürümlerini ve durumlarını listeler (hazırlanıyor, incelemede, yayında, reddedildi...). 'Hangi sürüm incelemede takıldı' sorusunun cevabı burada.
Inputs: uygulama_id (required), limit.
appstore__testflight_gruplariBRead-only
Uygulamanın TestFlight beta gruplarını ve her gruptaki test kullanıcı sayısını listeler.
Inputs: uygulama_id (required).
appstore__uygulamalarARead-only
App Store Connect hesabındaki uygulamaları listeler. Her uygulamanın adını, bundle ID'sini, App Store ID'sini ve birincil dilini döndürür. Diğer araçların çoğu buradaki 'id' değerini ister.
Inputs: limit, isim_filtresi.
appstore__yorumlarARead-only
Bir uygulamanın App Store müşteri yorumlarını getirir. Puana veya ülkeye göre süzülebilir, en yeniden eskiye sıralanır. Yorumları özetlemek, şikâyetleri bulmak veya cevap taslağı hazırlamak için kullan. Yoruma daha önce yanıt verilmişse onu da gösterir.
Inputs: uygulama_id (required), puan, ulke, limit, +1 more.
appstore__yorum_yanitlaADestructive
Bir App Store yorumuna geliştirici yanıtı yazar. Yanıt Apple incelemesinden geçtikten sonra yayınlanır.
Inputs: yanit (required), yorum_id (required), onayla.
magaza__abonelik_karsilastirARead-only
Aynı uygulamanın aboneliklerini App Store ve Google Play'de yan yana karşılaştırır: ürün kimlikleri, süreler ve istenen ülkedeki fiyatlar. İki mağaza arasındaki fiyat farklarını ve eksik ürünleri yakalar.
Inputs: uygulama (required), ulke.
magaza__cagirADestructive
App Store Connect ve Google Play API'lerinde herhangi bir operasyonu çalıştırır. Operasyon adını önce magaza__endpoint_ara ile bul. Veri değiştiren işlemler (POST/PATCH/PUT/DELETE) onayla=true verilmeden çalışmaz.
Inputs: magaza (required), operasyon (required), govde, onayla, +1 more.
magaza__endpoint_araARead-only
App Store Connect ve Google Play API'lerinin tamamında uç nokta arar. Hazır araçlar arasında işini görecek bir şey yoksa önce bunu kullan: aradığın işlemin gerçek operasyon adını, parametrelerini ve HTTP yöntemini döndürür. Sonucu magaza__cagir ile çalıştırabilirsin. Örnek sorgular: 'abonelik fiyat', 'testflight tester', 'crash rate'.
Inputs: sorgu (required), limit, magaza.
magaza__genel_bakisARead-only
İki mağazadaki uygulamaları tek listede gösterir ve aynı ürünün iOS/Android eşlerini yan yana getirir. 'Nerede neyim var' sorusunun tek çağrılık cevabı.
Inputs: no named parameters.
magaza__iap_teshisARead-only
'Kullanıcı parayı ödedi ama premium göremiyor' tipi sorunları teşhis eder. Uygulamanın iki mağazadaki satın alma kurulumunu tek tek kontrol eder: ürünler yayında mı, istenen ülkede fiyatı var mı, abonelik aktif mi. Play satın alma token'ı verirsen onu da doğrular.
Inputs: uygulama (required), ulke, play_token.
magaza__semaARead-only
Bir operasyonun istek gövdesinin nasıl olması gerektiğini gösterir. POST/PATCH çağrılarından önce, gövdeyi doğru kurmak için kullan.
Inputs: magaza (required), operasyon (required).
play__abonelik_fiyatlariARead-only
Bir Play aboneliğinin temel planındaki ülke ülke fiyatlarını getirir. Listelenmemiş ülkeler için 'diger_bolgeler' yedek fiyatına da bakar.
Inputs: urun_id (required), paket_adi (required), ulke, plan_id.
play__aboneliklerBRead-only
Uygulamanın aboneliklerini ve temel planlarını (base plan) listeler. Her planın süresi, durumu ve fiyatlandırıldığı ülkeler döner.
Inputs: paket_adi (required), limit, arsivi_dahil_et.
play__cokme_oraniARead-only
Android vitals çökme oranını getirir (Play Developer Reporting). 'Uygulamam neden çöküyor, ne zamandan beri arttı' sorularının başlangıcı.
Inputs: paket_adi (required), gun.
play__iade_edilenlerARead-only
İptal edilmiş, iade edilmiş veya geri alınmış satın almaları listeler. Kullanıcının erişimini kesmen gerekip gerekmediğini anlamak için. Google yalnızca son 30 günü verir; daha eskisi API'de yoktur.
Inputs: paket_adi (required), limit, sadece_urunler.
play__kanallarARead-only
Uygulamanın yayın kanallarını (internal, alpha, beta, production) ve her kanaldaki sürümleri gösterir. Hangi sürümün hangi kanalda, yüzde kaç kullanıcıya açık olduğunu söyler. Not: Play bu bilgiyi yalnızca bir düzenleme oturumu içinden verir; araç oturumu kendi açar ve hiçbir şey commit etmeden kapatır. Bu yüzden salt-okunur modda bile ağa POST+DELETE gider (uygulamada hiçbir şey değişmez) ve servis hesabının sürüm yönetme yetkisi olmadan araç çalışmaz.
Inputs: paket_adi (required).
play__satin_alma_dogrulaBRead-only
Bir satın alma token'ını doğrular ve durumunu döndürür. 'Bu kullanıcının aboneliği gerçekten aktif mi' sorusunun cevabı. Abonelik veya tek seferlik ürün, ikisi de desteklenir.
Inputs: token (required), paket_adi (required), tur.
play__urunlerARead-only
Tek seferlik uygulama içi ürünleri listeler. Yeni ürün modeline geçmiş uygulamalarda oneTimeProducts, geçmemişlerde eski inappproducts uç noktası kullanılır — bu araç ikisini de dener, hangisinin çalıştığını söyler.
Inputs: paket_adi (required).
play__uygulamalarARead-only
Servis hesabının eriştiği Google Play uygulamalarını listeler. Diğer play__ araçlarının istediği paket adını (packageName) buradan al. Not: bu liste Play Developer Reporting API'sinden gelir, çünkü Android Publisher API'sinde uygulama listeleme uç noktası yoktur.
Inputs: limit.
play__yorumlarARead-only
Google Play kullanıcı yorumlarını getirir. Play yalnızca son ~1 haftanın yorumlarını API'den verir; daha eskisi için Play Console dışa aktarımı gerekir.
Inputs: paket_adi (required), dil, limit.
play__yorum_yanitlaADestructive
Bir Google Play yorumuna geliştirici yanıtı yazar. Yanıt herkese açık yayınlanır ve geri alınamaz; onayla=true verilmeden çalışmaz.
Inputs: yanit (required), yorum_id (required), paket_adi (required), onayla.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 27 tools
The appstore__/play__ namespaces plus the magaza__ cross-store tools make most purposes clearly distinct (list versions vs. list builds vs. list reviews vs. reply to review). The only real overlap is the meta-tool trio (endpoint_ara, cagir, sema) which can reach any operation that the specific tools already wrap, so an agent could occasionally pick cagir where a dedicated tool would be better. Descriptions mostly resolve this by describing a clear workflow (find → schema → call).
All names are lowercase snake_case with a consistent platform prefix (magaza__, appstore__, play__), which gives a strong predictable grouping. The internal pattern mixes pure-resource nouns (uygulamalar, surumler, yorumlar) with resource_action forms (yorum_yanitla, metin_guncelle, satin_alma_dogrula), a minor deviation but still readable and internally consistent within each namespace.
At 27 tools the set is heavy, sitting just above the 25-tool threshold, though the surface spans two independent platforms (App Store + Play) across ~10 resource types each, which explains most of the count. The three generic meta-tools (endpoint_ara, cagir, sema) partially overlap with the dedicated wrappers, so a handful of tools could arguably be collapsed. Borderline but largely justified by the domain breadth.
Coverage is strong: apps, versions, builds, reviews (with replies), subscriptions, IAP products, pricing, sales reports, purchase verification, refunds, crash rate, plus cross-store comparison and purchase diagnosis. Dedicated gaps exist (no Play metadata update, no build upload/submit-for-review tool), but magaza__cagir/endpoint_ara/sema provide an escape hatch to the full App Store Connect and Play APIs, so agents are unlikely to hit a dead end.
Maintenance
Related MCP Connectors
Run App Store Connect from your IDE: pricing, listings, screenshots, releases, AI visibility.
App Store Connect operator for AI agents: icons, TestFlight builds, listings, IAP, rejection fixes.
AI-agent operations for App Store Connect and Google Play, with approval before live publishing.
AI-agent operations for App Store Connect and Google Play, with approval before live publishing.
Related MCP Servers
- AlicenseAqualityDmaintenanceManages App Store Connect and Google Play Console metadata, releases, and ASO workflows locally through MCP tools, enabling store management directly from AI clients without manual console navigation.109 npm3MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to manage Apple App Store Connect operations including app management, TestFlight, analytics, reviews, subscriptions, and more through 54 tools.61122 npm11MIT
- AlicenseNot gradedqualityBmaintenanceAutomate App Store Connect from your AI agent. Manage versions, metadata, builds, and submissions through natural language.15 npm8MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to manage Apple App Store Connect resources like apps, builds, TestFlight, and reviews through natural language.20MIT