Look up a single app by its store ID. Returns app metadata including name, developer, category, rating, reviews, installs (Android), and price. Works without an API key (free tier, limited daily use per IP). If the store is throttling, the result may be Sonar's stored copy: it then comes back as `{
Find apps in the App Store or Google Play by keyword, e.g. to get an app's store ID before calling other tools. Returns `{ source, data }`: `data` is the matching apps, compact by default (store ID, name, subtitle, developer, category, icon, rating, rating count, price, store URL, list position `ran
Calculate an ASO (App Store Optimization) audit score (0-100) for an app. Returns the overall score plus an itemized breakdown of checks (title length, keyword usage, screenshots, ratings, etc.) so you can identify what to improve. Works without an API key (free tier, limited daily use per IP).
Extract the most likely target keywords from an app's title and description, ranked by relevance. Useful for understanding what an app (yours or a competitor) is optimizing for. Works without an API key (free tier, limited daily use per IP).
Fetch user reviews for any app, live from the store (up to ~500 of the most recent or most helpful for the country). The star-rating filters and `limit` apply to that fetched window, so a narrow filter on a small app can return few or no reviews. Useful for sentiment analysis, feature-request mining
Estimate monthly revenue for an app, based on install counts, ratings, and category benchmarks. Returns the dollar estimate with its likely range (`monthly_range`), the install base it rests on (`installs`: estimate, low, high, source), a confidence grade (high/medium/low) with the factors behind it
Research a keyword and related terms. Returns up to 10 rows — the seed keyword plus the store's top autocomplete suggestions — each with difficulty (0-100), popularity score, and results count. Use this to find keywords worth targeting; for metrics on terms you already know, sonar_keyword_metrics is
Difficulty + popularity for a specific keyword (or up to 25 in bulk). Use this when you already know which keywords you care about — costs 1 credit per keyword. Works without an API key for up to 5 keywords/day (free tier, per IP); an API key removes that cap. Use sonar_keyword_search instead when y
Get autocomplete suggestions for a seed keyword from the App Store or Google Play, in the order the store shows them. List position is the only demand signal: the `priority` field is 0 on Google Play and currently 0 on the App Store as well. Lighter and faster than sonar_keyword_search — use when yo
Get a store top chart (free / paid / grossing, overall or by category) with day-over-day movement: per-app rank delta, apps new to the chart, biggest movers and apps that dropped out. Use to see what's rising in a market or category. Note: summary, movers and droppedApps always describe the full top
List the apps tracked in the caller's Sonar workspace (own apps + competitors), each with its latest snapshot (rating, review count, version, installs). Returns the Sonar app UUIDs needed by sonar_get_app, sonar_app_keywords, sonar_app_rankings, and sonar_app_changes. Cursor-paginated (default 100 p
Get details for one tracked app in the caller's Sonar workspace: store metadata plus daily snapshots of rating, review count, version, and installs. Compact by default (listing basics + the 7 newest snapshots); pass fields: "full" for the description, screenshots, release notes and up to 90 snapshot
List the keywords tracked for an app in the caller's Sonar workspace, with latest difficulty, popularity, results count, note, and starred_at (favorite/target marker) per keyword. Returns the tracked-keyword ids used by sonar_update_keyword_note and sonar_star_keyword, and the keyword_ids used by so
Rank history for an app's tracked keywords over the requested window. Compact by default: each keyword's current rank and status, best rank, positions gained and a newest-first daily `ranks` list (a rank, "unranked" = checked but not found, null = no check that day). Pass fields: "full" for the per-
SERP history for one tracked keyword — which apps ranked in the top results on each measured day, newest first (compact by default: no icon URLs; fields: "full" adds them). Use this to see who competes on a keyword and how the top spots shifted over time. The keyword must be tracked in the caller's
Keywords a tracked competitor currently ranks for (last 7 days of SERP data), with difficulty and popularity per keyword. Pass own_app_id for gap analysis: keywords where the competitor ranks but your app doesn't are marked gap=missing. Cursor-paginated (default 50 per page). Requires an Indie plan
The full competitive keyword picture for one of your own apps vs every tracked competitor, in one call: live stats (keyword gaps where competitors rank and you don't, winnable gaps, competitors climbing on your tracked keywords, keywords you lead), the top gap/threat/lead rows with metrics, and the
List every product in your workspace (unpaginated): each product's id, name, country, competitor count, and its linked store versions (Sonar app id, store, store_id, name). Product ids are what sonar_track_app, sonar_track_competitor, sonar_remove_competitor, sonar_delete_product, and the screenshot
List your alert subscriptions — each rule defines a change type (rank drops, review spikes, etc.), its scope (a specific app or org-wide), threshold, and whether it's enabled. Requires an Indie plan (trial counts).
The detected alert events for your workspace, newest first — the same feed as the in-app Recent Alerts panel and the email digest: rank drops/gains, top-10 entries/exits, new rankings, rating drops, review spikes, and competitor changes, each with a type-specific payload (app/keyword names, old vs n
The dashboard's computed scoreboard for one of your apps in a single call: visibility index and share of voice (with 7-day deltas and a daily spark), ranked / top-10 keyword counts with movement, best rank, the biggest 7-day improvements and drops, the rank-distribution trend, and the actionable opp
Keywords Sonar's discovery engine surfaced for one of your tracked apps but that aren't tracked yet — ranked finds (the app already ranks, unnoticed), competitor gaps, and AI/autocomplete-sourced ideas — each with popularity, difficulty, AI relevance, and an opportunity score (0-100, best first). Th
The latest AI review analysis for a tracked app (your own or a competitor): what users praise and complain about as named themes with frequency, verbatim quotes, and trend movement (new / persisting / growing / improving / resolved), plus overall sentiment, surfaced feature requests, and what change
The review responder's configuration for an own iOS app: whether it is switched on, manual vs auto mode (auto posts AI replies after a delay, only for reviews written after auto was enabled and within the star range), the reply instructions, sign-off, reply language, last sync, plus whether App Stor
An own iOS app's App Store reviews (synced from App Store Connect every 5 minutes) with their reply state: the AI draft or your text, English translations of non-English reviews and drafts, hold reasons (needs_human, quota, daily_cap), schedule time, and any live App Store response. Newest first, wi
The whole portfolio's health in one call — for orgs managing many apps: per-app KPIs (visibility + 7-day delta, ranked/top-10 counts, net rank movement, rating, review count), org-wide totals, the biggest keyword movers in both directions, a needs-attention triage list (visibility drops, rating drop
App Store Connect sales for one of your own iOS apps: daily first-time downloads, redownloads, in-app purchase units and approximate USD proceeds (`proceeds_usd_approx`, converted with a static FX table — present it as approximate), window totals, and a per-country breakdown sorted by downloads. Sam
App Store Connect App Analytics for one of your own iOS apps: the impressions → product page views → downloads funnel with conversion rates (`page_view_rate`, `download_rate`) and App Store search share, impressions by source (App Store search, browse, app referrer, web referrer…), plus daily instal
WRITE tool — creates a product in the caller's Sonar workspace and starts tracking the given app(s). A product is the cross-store unit (one iOS + one Android app, or just one of either). Returns the product id and the Sonar app ids needed by sonar_track_keywords and sonar_track_competitor. Own apps
WRITE tool — links the second-store version of an existing Sonar product (e.g. the product already tracks the iOS app and you want to add the Android version, or vice versa). Each product holds at most one iOS + one Android app; to start tracking a brand-new app, use sonar_create_product instead. Re
WRITE tool — adds a competitor app under a Sonar product so its keywords and rankings get tracked alongside the product's own app. The product must already have its own app linked in the same store as the competitor. Requires an Indie plan (trial counts) and an authorized Sonar account or an API key
WRITE tool — starts daily rank tracking for one or more keywords on an app in the caller's Sonar workspace. Idempotent: re-posting the same terms reports them as already_tracked instead of creating duplicates. Returns per-keyword outcomes (created / already_tracked / failed). Tracked keywords count
WRITE tool — sets or clears the note on a tracked keyword in the caller's Sonar workspace (e.g. why it's tracked, an optimization hypothesis, a reminder). Idempotent: re-sending the same note is a no-op. Requires an Indie plan (trial counts) and an authorized Sonar account or an API key with the wri
WRITE tool — stars or unstars a tracked keyword in the caller's Sonar workspace. A star marks the keyword as a favorite/target the user is actively pursuing; starred keywords carry a starred_at timestamp in sonar_app_keywords results. Idempotent: re-starring refreshes the timestamp, unstarring a non
WRITE tool — runs an AI keyword discovery scan on a tracked competitor: generates the search terms the competitor's listing is optimized for (brand terms included), queues them for SERP verification, and verifies the first batch inline (~30s), recording both apps' ranks. Returns generated/queued/ver
WRITE tool — generates a fresh AI competitive insight for one of your own apps: clusters the keyword gaps vs your competitors into named opportunity themes (with a why-now narrative and per-keyword metrics), writes threat narratives for competitors climbing on your keywords, and diffs against the pr
WRITE tool — generates a fresh AI review analysis for a tracked app from its recent reviews (praise/complaint themes, sentiment, feature requests, trend vs the previous run). At most one analysis per app+country every 90 days (429 with the next available time while in cooldown — use sonar_review_ins
WRITE tool — stop tracking one keyword/app pair in the caller's Sonar workspace. Identify the pair by its tracked-keyword id (from sonar_app_keywords). Equivalent to sonar_untrack_keywords with a single id; that tool removes several (or all) of an app's keywords in one call. Requires an Indie plan (
WRITE tool — bulk-untrack keywords for an app in the caller's Sonar workspace. Pass `all: true` to remove every tracked keyword, OR `ids: [...]` to remove specific ones (exactly one of the two). For a single keyword, sonar_delete_tracked_keyword is equivalent. Requires an Indie plan (trial counts) a
WRITE tool — untrack an app in the caller's Sonar workspace. Deletes the workspace's tracked keywords for it (with their notes and stars), its discovered keywords, and its competitor links, and detaches it from its product — deleting the product, and that product's screenshot sets, if no other app i
WRITE tool — delete a product in the caller's Sonar workspace and untrack every app linked to it, with their tracked keywords, discovered keywords, and competitor links. The product's screenshot sets are deleted too. Shared store data (app metadata, snapshots, rank history) is not deleted. Returns {
WRITE tool — remove a competitor from a product in the caller's Sonar workspace. Drops the competitor link under every own app of the product; if no other own app in the workspace still references the competitor, the competitor app is untracked as well. 404 when the product has no such competitor. R
WRITE tool — create or update an alert subscription in the caller's Sonar workspace. Upserts on (type + scope): re-submitting the same type/scope updates the existing rule. Omit `threshold` for the per-type default; omit `scope_app_id` for an org-wide rule. Requires an Indie plan (trial counts) and
WRITE tool — delete an alert subscription in the caller's Sonar workspace. Requires an Indie plan (trial counts) and an authorized Sonar account or an API key with the write scope.
WRITE tool — switch the review responder on/off for an own iOS app and update its instructions or auto-mode policy (partial update; omitted fields keep their value). Turning auto mode on only affects reviews written afterwards; anything the AI flags as needing a human is held. Requires an Indie plan
WRITE tool — write a fresh AI reply draft for a review using the app's instructions (and an optional hint), with English translations. Counts against the monthly AI-draft allowance, then 1 credit per draft. Never posts. Tip: agents can skip this and write the reply themselves with sonar_update_revie
WRITE tool — replace a review's reply text (not metered, doesn't post). Use sonar_post_review_reply to publish. Requires an Indie plan (trial counts) and an authorized Sonar account or an API key with the write scope.
WRITE tool — PUBLIC ACTION: publishes the reply on the App Store under the developer's name (now, or after delay_minutes). Overwrites an existing response (Apple keeps one per review and marks it edited). Apple shows it within ~24h: status pending_publish, then published. Needs an Admin-role App Sto
WRITE tool — mark a review as not needing a reply (also cancels a scheduled post). Requires an Indie plan (trial counts) and an authorized Sonar account or an API key with the write scope.
WRITE tool — cancel a scheduled reply (manual or auto mode) before it posts; it goes back to draft. Requires an Indie plan (trial counts) and an authorized Sonar account or an API key with the write scope.
The layout-format reference for Sonar screenshot sets: static text, so one call per session is enough. It documents the layout JSON schema, coordinate system, image handling (remote URLs), flowing background shapes, fonts, translation overrides, and the recommended workflow.
List the device sizes supported for app-store screenshot sets, with their canvas dimensions (the pixel coordinate space all layouts use) and which store each belongs to — including the landscape App Store creative-asset canvases (category "creative": product page header and search results asset). Pi
List a product's app-store screenshot sets (metadata only: store, device size, locales, studio_url). Use sonar_get_screenshot_set for full layouts. Requires an Indie plan (trial counts).
Create an app-store screenshot set for a product, from your own `screens` layouts or a built-in template. The layout JSON format and template ids are documented by sonar_screenshot_layout_guide. The set is immediately visible/editable for humans in the Screenshot Studio (studio_url in the response).
Fetch a screenshot set in full: every screen's layout JSON plus per-screen translation overrides keyed by locale. By default inline image data is replaced with placeholders to keep the response readable. Requires an Indie plan (trial counts).
Rename a screenshot set, replace its extra-locale list, and/or reorder its screens. Returns the updated set (with image data stripped). Requires an Indie plan (trial counts) and an authorized Sonar account or a write-scope API key.
Permanently delete a screenshot set and everything in it (screens, translations). Irreversible — confirm with the user before deleting work they may want. Requires an Indie plan (trial counts) and an authorized Sonar account or a write-scope API key.
Append a screen to a screenshot set (at the end; reorder with sonar_update_screenshot_set). Requires an Indie plan (trial counts) and an authorized Sonar account or a write-scope API key.
Replace one screen's layout in a screenshot set. Whole-document replace — fetch the current layout, modify it, send it back. The change shows up immediately in the Screenshot Studio for human review. Requires an Indie plan (trial counts) and an authorized Sonar account or a write-scope API key.
FAQ
Вопросы
Как установить Sonar?
Скопируйте на этой странице конфигурацию http для Cursor, Claude Desktop, Claude Code или VS Code. Она использует установку издателя, а не прокси PlugMCP.
Нужен ли API-ключ для Sonar?
Издатель указывает следующие переменные окружения: SONAR_API_KEY, SONAR_API_URL.
Какой транспорт использует Sonar?
Sonar доступен по HTTP.
Когда Sonar проверялся в последний раз?
Последняя проверка: 2026-11-15. ASO tools for AI agents: keyword research, rank tracking, competitor analysis (iOS & Android).
От издателя
Документация
@sonarapp/mcp
The official Sonar MCP server — App Store Optimization tools for AI agents.
Lets Claude Desktop, Claude Code, Cursor, Cline, and any Model Context Protocol-compatible client look up apps, research keywords, audit ASO, mine reviews, and estimate revenue across the iOS App Store and Google Play. Powered by Sonar.
Tools
55 tools covering the whole Sonar REST API, grouped by what they need.
Read tools — stateless (any plan with credits)
Tool
What it does
Works without a key
sonar_app_lookup
Look up app metadata by store ID
Yes
sonar_app_search
Search apps by keyword (returns store ranking order)
Yes
sonar_app_aso_score
ASO audit score (0-100) with itemized checks
Yes
sonar_app_extract_keywords
Extract target keywords from an app's listing
Yes
sonar_app_reviews
Fetch reviews with rating filters and sort options
—
sonar_app_revenue
Estimate monthly revenue with a confidence grade
—
sonar_keyword_search
Keyword research (difficulty, popularity, related terms)
—
sonar_keyword_metrics
Difficulty + popularity for specific keywords (up to 25 per call)
Yes (5 keywords/day)
sonar_keyword_suggestions
Autocomplete suggestions from the store
Yes
sonar_top_charts
Top free/paid/grossing chart with day-over-day movement
Yes
Stateless tools work on any plan with credits (API Credits, Indie or Agency), for both iOS and Android. The ones marked "Yes" also run keyless on the free tier (see "Try it free" below).
Read tools — your workspace (Indie plan)
Tool
What it does
sonar_list_products
List your products with their linked store versions and competitor counts
sonar_list_apps
List your tracked apps with latest snapshots (rating, reviews, installs)
sonar_get_app
App detail + up to 90 days of snapshot history
sonar_app_overview
Dashboard scoreboard for an app: visibility, share of voice, movement, opportunities
sonar_app_keywords
Keywords tracked for an app, with difficulty, popularity, notes and stars
Workspace reads require an Indie plan or higher (an active trial counts); the default read-scope key is enough.
Read tools — Agency plan
Tool
What it does
sonar_portfolio
Portfolio rollup: per-app KPIs, biggest movers, needs-attention list, top opportunities
sonar_app_sales
App Store Connect sales: downloads, redownloads, IAP units, approximate proceeds
sonar_app_engagement
App Store Connect funnel: impressions, page views, downloads, sources, sessions
These require the Agency plan (an Agency trial counts) and return 403 on other plans. sonar_app_sales and sonar_app_engagement are iOS-only and also need an App Store Connect connection at trysonar.app/settings/connections; engagement data needs an Admin-role App Store Connect key.
Write tools (Indie plan + write scope)
Tool
What it does
sonar_create_product
Create a product in your Sonar workspace and start tracking its app(s)
sonar_track_app
Link the second-store version (iOS ↔ Android) of an existing product
sonar_track_competitor
Add a competitor app under a product
sonar_remove_competitor
Remove a competitor from a product
sonar_delete_product
Delete a product and untrack its apps
sonar_untrack_app
Untrack an app and its tracking data
sonar_track_keywords
Start daily rank tracking for keywords on an app (bulk, idempotent)
sonar_update_keyword_note
Set or clear the note on a tracked keyword
sonar_star_keyword
Star or unstar a tracked keyword (mark it as a target)
sonar_delete_tracked_keyword
Stop tracking one keyword/app pair
sonar_untrack_keywords
Bulk-untrack an app's keywords (selected IDs or all)
sonar_scan_competitor
Run an AI keyword discovery scan on a competitor (read results with sonar_competitor_keywords)
sonar_analyze_competitors
Generate a fresh AI competitive insight for one of your apps (7-day cooldown)
sonar_generate_review_insights
Generate a fresh AI review analysis for a tracked app (90-day cooldown)
sonar_set_alert
Create or update an alert rule
sonar_delete_alert
Delete an alert rule
Write tools mutate your workspace and require an Indie plan or higher (an active trial counts) plus either an OAuth sign-in on the hosted endpoint (which carries write access) or an API key created with the write scope. The two AI generation tools, sonar_analyze_competitors and sonar_generate_review_insights, need a paid plan and are not available during the trial. The server enforces all of this — without it, calls return a 403 explaining what to fix.
Together these close the loop for agents: set up tracking with the write tools, then read back rankings, changes, and gap analyses with the workspace tools.
Screenshot Studio (Indie plan)
Tool
What it does
Scope
sonar_screenshot_layout_guide
Layout-format reference; read it once before authoring layouts
none
sonar_screenshot_devices
Supported device sizes and their canvas dimensions
read
sonar_list_screenshot_sets
A product's screenshot sets (metadata only)
read
sonar_get_screenshot_set
A full set: every screen's layout plus translation overrides
read
sonar_create_screenshot_set
Create a screenshot set for a product
write
sonar_update_screenshot_set
Rename a set, replace its locales, or reorder its screens
write
sonar_delete_screenshot_set
Delete a set and everything in it
write
sonar_add_screenshot
Append a screen to a set
write
sonar_update_screenshot
Replace one screen's layout
write
sonar_delete_screenshot
Delete one screen (a set keeps at least one)
write
sonar_set_screenshot_translations
Write a locale's translation overrides
write
sonar_export_screenshots
Render store-ready PNGs into one local ZIP per locale
read
Agents author screenshot sets as layout JSON; humans review and fine-tune the same sets in the Screenshot Studio. The layout guide is embedded in the server and needs no key. sonar_export_screenshots writes files on the machine running the server, so it's available over stdio only, not on the hosted endpoint.
Hosted endpoint — no install, no API key
OAuth-capable MCP clients (Claude Code, claude.ai custom connectors) can skip both the npm install and the API key entirely:
claude mcp add --transport http sonar https://trysonar.app/mcp
The first tool call that needs your account opens a browser sign-in — approve it with your Sonar login and the agent has full access to the workspace you own (read + write). Clients without OAuth support can pass an API key instead: --header "Authorization: Bearer aso_...".
ChatGPT submission and hosted behavior
Submit https://trysonar.app/mcp/chatgpt to OpenAI. This endpoint returns tool-level sign-in challenges; /mcp retains HTTP 401 challenges for Claude and other MCP clients. Both advertise OAuth per tool. Anonymous store lookups can run without linking; workspace tools return a native sign-in challenge when authorization is missing or expired. Connect an existing Sonar account and approve access to the workspace you own. Existing account permissions and entitlements apply.
The ChatGPT endpoint requires resource-bound JWT access tokens for its canonical /mcp/chatgpt audience; the existing /mcp endpoint retains Clerk opaque-token support. Provider configuration and an end-to-end login must be verified before submitting the ChatGPT endpoint.
The hosted catalog excludes sonar_export_screenshots, which writes ZIP files to the local MCP host. It remains available over stdio. A native directory listing requires separate OpenAI review and publication; hosting an MCP endpoint does not itself create a listing.
Try it free — no API key needed
The server runs without a key in free mode: sonar_app_search, sonar_app_lookup, sonar_app_aso_score, sonar_app_extract_keywords, sonar_keyword_suggestions, and sonar_top_charts share a free allowance of 30 requests/day per IP, and sonar_keyword_metrics (keyword difficulty + popularity) gets 5 keywords/day. Just install it with no env block and ask your agent about ASO. When you hit the limit, the error tells you how to sign up.
Get an API key
For everything else (tracking, rankings, competitors, higher limits) you'll need a Sonar API key — get one at trysonar.app/developers.
The cheapest path is prepaid API credits — packs from $10 (1,000 credits), with 50 free credits on signup and no subscription. Built specifically for this use case. See pricing.
Install
Claude Desktop
Add to your config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
The MCP server is a thin client around Sonar's REST API — it stores nothing locally and no data is logged by this package itself.
Data collected: tool inputs (app IDs, keywords, country codes) are sent to Sonar's API over HTTPS to produce results; authenticated requests include your API key as a Bearer token. Sonar logs API requests (endpoint, status, timing) for rate limiting and abuse prevention.
Data usage: inputs are used solely to serve the request (keyword metrics, app lookups, etc.); resulting JSON is returned to your AI client.
Storage & retention: the package keeps no state on disk. Server-side request logs are retained for 90 days; workspace data (tracked apps/keywords) persists in your Sonar account until you delete it.
Third-party sharing: no user data is sold or shared with third parties; queries against public app-store data (Apple, Google) contain no personal information.
"SONAR_API_KEY is not set — running in free mode" — Expected if you haven't configured a key: the free tools keep working with per-IP daily limits. If you DID configure a key, the MCP client did not pass the env var through — check the env section of your client's config file. Some clients require an absolute path to npx — try which npx and use that.
"Authentication failed" — Your key is invalid, expired, or your subscription lapsed. Visit trysonar.app/developers to check.
"Access denied. This endpoint may require an Indie plan subscription" — The 10 stateless read tools work on any plan with credits. The workspace read, write, and Screenshot Studio tools require an Indie plan or higher (an active trial counts); write tools additionally need an API key created with the write scope. sonar_portfolio, sonar_app_sales, and sonar_app_engagement require the Agency plan, and the two AI generation tools need a paid plan (not a trial). If you're on a setup or trial-expired plan, reactivate first.
Companion: CLI
Prefer the terminal? Use @sonarapp/cli (sonar binary) — same data, same API key.