AppmanAi

com.appmanaiv1.0.0更新於 Sep 30, 2026

App Store & Google Play data for ASO: keywords, rankings, charts, reviews in 100+ countries.

已驗證Streamable HTTP可網頁執行Web Search & ScrapingBusiness & CommerceData & Analytics

概覽

AI 產生的概覽

讓助理取得 App Store 與 Google Play 的即時 ASO 資料：涵蓋 100 多個國家的關鍵字、排名、排行榜、評分與評論。

功能
這是一個遠端 MCP 伺服器，提供 35 個唯讀工具用於應用程式商店優化。它能把應用程式名稱解析成套件 ID，依熱度與難度分析關鍵字，追蹤應用程式在單一關鍵字的歷史排名與全球排名，列出分類排行榜，並回傳評分與使用者評論。它也能產生關鍵字清單與改寫商店文案，並註冊 32 個以提示為基礎的斜線指令來執行多步驟 ASO 工作流程。
適用情境
當你需要目前的商店資料、而不是模型記憶中的舊資訊時使用：關鍵字研究與競品差距分析、排名追蹤與排名下滑歸因、排行榜與分類標竿比較，或從評論中挖掘使用者抱怨。適合應用程式行銷人員、獨立開發者與跨多國營運的 ASO 分析師。
執行需求
遠端可串流 HTTP 端點，不需在本機安裝。認證採用 OAuth 2.1，在瀏覽器授權一次即可，不需貼上 API 金鑰。呼叫以點數計費：新帳號贈送 200 點且不需綁卡，免費方案每月 100 點，付費方案每月 1,000 點。參考類與帳號類工具免費。
安裝前請注意
多數工具會消耗點數（每次呼叫 2–15 點，1 點 = 0.02 美元），助理可能很快用完餘額；每次結果都會顯示剩餘點數，也可用 user_balance 隨時查詢。付費方案為每月 20 美元或每年 200 美元。工具被描述為唯讀，但 generate_app_metadata 會產生改寫後的商店文案，發佈前應自行審核。查詢內容與帳號用量會傳送到提供方伺服器。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AppmanAi，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "appmanai-mcp": {
      "type": "http",
      "url": "https://appmanai.com/api/mcp"
    }
  }
}

README

[AppmanAi — give your AI real App Store and Google Play data]

AppmanAi MCP

Keyword demand, rank history, top charts, competitors, reviews and ratings — across 100+ countries, answered inside your chat instead of a dashboard.

[Website] [Docs] [Tools] [License]


[Add to Claude] [Add to Cursor] [Add to VS Code]

Without AppmanAi

Ask an assistant about your app's market and it answers from training data — a snapshot of some stores, some countries, some year ago:

  • Keyword advice with no idea what people actually search for
  • "Competitors" it inferred from a name rather than the store's own graph
  • Rank claims it cannot check, stated with the same confidence as facts
  • Nothing at all for the 90+ countries outside the US

With AppmanAi

Your agent calls the stores. Every number in the answer came back from a live query, and the agent tells you what each call cost.

txt
Which keywords do my three UK competitors rank top-10 for that I don't?
txt
Profile the keyword "habit tracker" on the US App Store — is it worth chasing?
txt
My rank for "meditation" dropped 12 places last week. Was that me, or the algorithm?
txt
What do users actually complain about in the reviews of com.example.app?
txt
Where in the world does "budget planner" have enough demand to justify a launch?

Install

AppmanAi is a remote MCP server. There is nothing to download and no API key to paste — you add one URL, sign in, and the tools appear:

https://appmanai.com/api/mcp

Authentication is OAuth 2.1: your client opens a browser, you approve once, and it stores the token. New accounts get 200 free credits, no card.

ClientHow
Claude
web · desktop · mobile

Add AppmanAi to Claude →

Or: Settings → Connectors → Add custom connector, paste the URL, Allow.

Claude Code
bash
claude mcp add --transport http appmanai https://appmanai.com/api/mcp
Cursor

One-click install → · or add to mcp.json:

json
{ "mcpServers": { "appmanai": { "url": "https://appmanai.com/api/mcp" } } }
VS Code

One-click install → · or add to mcp.json:

json
{ "servers": { "appmanai": { "type": "http", "url": "https://appmanai.com/api/mcp" } } }
Codex
bash
codex mcp add appmanai --url https://appmanai.com/api/mcp
Gemini CLI
bash
gemini mcp add appmanai https://appmanai.com/api/mcp --transport http
Anything else

Bridge it over stdio with mcp-remote:

json
{ "mcpServers": { "appmanai": { "command": "npx", "args": ["-y", "mcp-remote", "https://appmanai.com/api/mcp"] } } }
What the three steps look like

1 · Paste the URL as a custom connector

[Claude's Add custom connector dialog with the AppmanAi URL]

2 · Sign in and click Allow

[The AppmanAi authorize screen]

3 · The tools answer in chat

[AppmanAi answering a keyword question in Claude]

Tools

35 read-only tools. Costs are in credits and are the real numbers the server charges — this section is generated from the live catalogue by scripts/generate-tool-table.mjs, so what is published here cannot drift from what you are billed.

Apps — 7 tools, 2–8 credits
ToolCreditsWhat it does
app_search2Search a store for apps matching a name or phrase. Returns matching apps with their package ids — the way to resolve a name into a package id for the other tools.
app_similar5List the apps the store itself considers similar to a given app (title, developer, icon). The quickest way to build a competitor set from one seed app.
app_metrics_metadata3Fetch the full store listing for one app (title, developer, ratings, category, metadata) by its package id. If you only have the app name, call app_search first to resolve it.
app_metrics_metadata_batch8Fetch store listings for a list of package ids in one call — the bulk form of app_metrics_metadata. Use it when comparing apps, instead of one call per app.
app_metrics_ratings_worldwide6An app's current rating and per-star vote counts in every country it is listed in. Use it to see where an app is rated well or badly; app_metrics_ratings_history tracks one country over time.
app_metrics_ratings_history5An app's average rating and star breakdown over time in one country — a dated series for charting whether a release helped or hurt. app_metrics_ratings_worldwide gives the current picture across all countries instead.
app_reviews4Read real user reviews of an app: author, star rating, text and date. Use it to find out what users actually complain about or praise.
Keywords by app — 7 tools, 2–12 credits
ToolCreditsWhat it does
keyword_app_metrics_rankings2Where one app currently ranks in search results for one keyword. The direct answer to "am I ranking for this?". A rank of 0 means the app is not in the results.
keyword_app_metrics_rankings_batch9One app's rank for a list of keywords in a single call. Use it to check a whole keyword set at once instead of calling keyword_app_metrics_rankings repeatedly. A rank of 0 means the app is not in the results.
keyword_app_metrics_rankings_history6One app's rank for a keyword over time — the series to chart when asking whether a change helped. Pick the window with period. A rank of 0 means the app is not in the results.
keyword_app_metrics_rankings_worldwide12One app's rank for a keyword in every country at once. Use it to find the markets where the app already ranks, before spending calls per country. A rank of 0 means the app is not in the results.
keyword_app_suggestions6List the keywords a specific app is recommended for / ranks on in a store/country, by its package id. The direct way to answer "what keywords does this app rank for?". If you only have the app name, call app_search first to resolve it. A rank of 0 means the app is not in the results.
keyword_app_competitors6List keywords that the competitors of one app rank for, with their popularity (SAP) and that app's own rank where it has one. Use it to find the gaps — keywords rivals own and this app does not. keyword_app_suggestions covers what the app itself already ranks for.
keyword_app_overlap7Given a set of apps, list the keywords they compete on, each with its popularity (SAP) and every app's rank for it. Use it to compare a whole competitor set head-to-head on one keyword list; keyword_app_competitors starts from a single app instead.
Keywords — 8 tools, 4–12 credits
ToolCreditsWhat it does
keyword_metrics4Get the ASO profile of a keyword: search-ads popularity (SAP), difficulty, and languages. Use it to judge whether a keyword is worth targeting.
keyword_metrics_sap4Get just the search-ads popularity (SAP, 0-100) of one keyword in a country, across both stores. The cheapest popularity check; keyword_metrics adds difficulty and languages.
keyword_metrics_sap_batch9Get the search-ads popularity (SAP) of many keywords in one call. Use it to rank a whole keyword list by demand before profiling the promising ones.
keyword_metrics_volatility8How much the store's ranking algorithm moved in one country over a period. High volatility means rank changes are the store's doing, not yours — check it before blaming a release.
keyword_metrics_volatility_worldwide12Ranking-algorithm volatility for one date across every country, so you can tell a global store change from a local one.
keyword_top_apps5List the apps that rank highest for a keyword in a store/country — the search results a user sees. Use it to find the incumbents / competitors for a keyword.
keyword_suggestions5Expand a seed keyword into related keyword suggestions for a store/country. Use it to grow a keyword list before profiling or checking ranks.
keyword_suggestions_worldwide10Expand a seed keyword into suggestions with their popularity (SAP), across all markets at once and without picking a store or country. The cheap first pass before narrowing down with keyword_suggestions or keyword_metrics.
Charts and categories — 5 tools, 2–6 credits
ToolCreditsWhat it does
category_top_apps5List the apps at the top of a category chart (top free, top grossing, top paid) in a country. Use it to see who leads a category; list_categories has the valid tags.
app_category_rankings3List every category chart an app currently appears in, with its rank in each. The place to start when you do not already know which chart matters.
app_category_rankings_single2An app's current position in a single category chart. Use it when you know exactly which chart you mean; app_category_rankings lists every chart the app appears in.
app_category_rankings_history6An app's position in a category chart across past days — the series to chart when asking whether an app is climbing or sliding.
app_category_start_rankings5For each app given, the rank it first held in a chart from a start date — the baseline to measure a campaign against.
Generation — 2 tools, 12–15 credits
ToolCreditsWhat it does
generate_keywords12Generate a keyword list for an app from its own store listing, each scored with its popularity (SAP) and the app's current rank where it has one. Use it to propose new keywords to target; keyword_app_suggestions reports what the app already ranks for.
generate_app_metadata15Rewrite an app store listing — title, short and long description — optimised for the keywords you pass and the store it targets. Takes the current copy directly, not a package id, so you can iterate on drafts; use app_metrics_metadata first if you want to start from a live listing.
Reference (free) — 3 tools, free
ToolCreditsWhat it does
list_countriesfreeList the countries AppmanAi covers, with languages and per-store support levels. Use it to confirm coverage or resolve a country code before other calls.
list_categoriesfreeList a store's category tree — category tags and the charts under each (top free, top grossing, top paid). Call it to get the exact tags the category tools take.
list_featuresfreeList which parts of the dataset are available for a store and country. Use it to check whether a kind of data exists for a market before spending credits looking for it.
Account (free) — 3 tools, free
ToolCreditsWhat it does
user_balancefreeShow the credit balance on the connected AppmanAi account, split into the monthly allowance and credits that never expire.
user_api_usagefreeSummarise this account's recent AppmanAi usage: credits spent, request count and a per-route breakdown over a window of days.
list_toolsfreeList every AppmanAi tool with what it costs in credits, plus the current balance. Answers "what can you do?" and "what will this cost?".

Free tools stay available at a zero balance, so an agent can always check coverage and its own budget.

Slash commands

The server registers 32 prompts, which appear as slash commands in clients that support them — /appmanai:keyword_gap in Claude, /keyword_gap in Cursor. Each one runs a whole workflow from a couple of arguments.

All 32 commands

Apps and competitors

CommandWhat it does
/find_appTurn an app name into the package id everything else needs
/app_profileFull store listing for one app in one country
/similar_appsThe competitor set the store itself considers adjacent
/compare_appsMany package ids in one call — a competitor table
/draft_metadataAI-written title, subtitle and description options

Keyword research

CommandWhat it does
/expand_keywordGrow one seed into related terms real users type
/keyword_profilePopularity, difficulty and language coverage for a term
/keyword_popularityThe raw search-ads demand number for a term
/score_keywordsSAP for a whole list — prune a brainstorm to a shortlist
/keyword_worldwideWhere in the world a term actually has demand
/app_keywordsThe recommended keyword set for one app
/generate_keywordsAI keyword ideas when the obvious terms are saturated
/competitor_keywordsThe terms your rivals already own
/keyword_gapClassic gap analysis — what they rank for and you don't

Rank tracking

CommandWhat it does
/keyword_rankOne app, one keyword, one country
/rank_historyThe dated series behind a position
/rank_reportOne app across a whole keyword list
/keyword_leadersThe incumbents you would have to displace
/rank_worldwideOne keyword across every covered country
/algorithm_checkWas that move the store, or was it you?
/algorithm_check_worldwideThe same check across every country

Charts and categories

CommandWhat it does
/top_chartsThe current leaderboard for a category and country
/app_chart_ranksEvery chart position one app holds
/chart_positionA single chart position — the cheapest check
/chart_historyChart trajectory over time
/launch_benchmarkWhere new apps actually enter the charts

Reviews and ratings

CommandWhat it does
/app_reviewsRaw reviews for an app
/rating_breakdownThe star histogram behind the average
/rating_historyHow the average rating moved

Reference data

CommandWhat it does
/check_coverageWhich countries are covered, in what depth
/category_idsThe category ids the chart tools expect
/feature_checkWhat data exists per store and country

Each is also listed, with its example prompts, in the prompt gallery.

Skills

skills/ holds Claude Skills — multi-step ASO workflows written on top of these tools. Copy a folder into .claude/skills/ and the workflow becomes available by name.

SkillWhat it produces
aso-keyword-auditA scored, prioritised keyword shortlist for one app in one market
competitor-gapThe keywords rivals own and you don't, ranked by reachability
rank-drop-triageA verdict on whether a rank drop was your listing or the algorithm
review-miningRecurring complaints and requests, grouped and sized

They are plain Markdown, they only call the read-only tools above, and each step carries its credit cost — read one before you run it.

Pricing

Credits, billed per call. No subscription needed to start.

FreeBase
Price$0$20 / month or $200 / year
On signup200 credits, no card—
Every month100 credits1,000 credits
Top-up packs—✓

1 credit = $0.02. A call costs 2–15 credits depending on how much work it is; the tool table lists every one. Reference and account tools are always free.

Every tool result ends with your remaining balance, and user_balance reports it on demand. Live numbers: appmanai.com/pricing.

The HTTP API

The same data is a plain REST API, for when you would rather not go through an agent:

bash
curl -G "https://appmanai.com/api/v1/keywords/metrics" \  -H "Authorization: Bearer $APPMANAI_KEY" \  --data-urlencode "store=ios" \  --data-urlencode "country=US" \  --data-urlencode "keyword=habit tracker"

openapi.yaml is the full, frozen spec — the same one the reference docs and the typed clients are generated from. Runnable examples in examples/: curl, Python, TypeScript.

Quickstart · Authentication · Rate limits · Errors · Full reference

Coverage

Which countries, which stores, and how far back the history goes — published in full, including the gaps: appmanai.com/coverage.

The list_countries, list_categories and list_features tools answer the same question from inside a chat, for free. Country missing? Tell us — demand is how we pick what to crawl next.

Support

The MCP server is hosted by us and is not open source. This repository holds the connector manifest, the API spec, the skills and the examples — all MIT licensed. See LICENSE.

來源：README.md，提交 04dbd57

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Sep 30, 2026