The com.getappniche/mcp MCP server provides live App Store and Google Play data for AI agents. It focuses on app discovery, ASO (App Store Optimization) keywords, and reviews to support downstream agent workflows that need up-to-date store content.

🛠️ Key Features

Live App Store data
Live Google Play data
App discovery
ASO keyword data
Reviews

🚀 Use Cases

Discover relevant apps using store listings
Retrieve ASO keywords for optimization research
Analyze or surface information from app reviews

⚡ Developer Benefits

Centralizes App Store + Google Play inputs for AI agents
Enables agent tooling around discovery, keyword research, and review data

⚠️ Limitations

Source description does not specify supported MCP tools, authentication, or performance characteristics.

GetAppNiche MCP — App Store & Google Play intelligence for AI agents

The Model Context Protocol surface of GetAppNiche: live App Store & Google Play data — app discovery with revenue & download data, ASO keyword scoring, historical metrics and review feeds — for Claude, Cursor, Codex, Gemini CLI and any other MCP-capable agent.

You probably don't need to run anything. The server is hosted:

code

https://api.getappniche.com/mcp        Streamable HTTP · JSON-RPC 2.0
Authorization: Bearer YOUR_API_KEY     app.getappniche.com → Settings → API Keys

Setup per client

Claude Code — one command, no restart:

bash

claude mcp add --transport http getappniche https://api.getappniche.com/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Cursor — .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

json

{
  "mcpServers": {
    "getappniche": {
      "url": "https://api.getappniche.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Claude Desktop — claude_desktop_config.json, then restart the app fully:

json

{
  "mcpServers": {
    "getappniche": {
      "command": "npx",
      "args": ["-y", "@getappniche/mcp"],
      "env": { "GETAPPNICHE_API_KEY": "YOUR_API_KEY" }
    }
  }
}

VS Code (Copilot agent mode) — .vscode/mcp.json:

json

{
  "servers": {
    "getappniche": {
      "type": "http",
      "url": "https://api.getappniche.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Windsurf — ~/.codeium/windsurf/mcp_config.json (the field is serverUrl):

json

{
  "mcpServers": {
    "getappniche": {
      "serverUrl": "https://api.getappniche.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Codex CLI — ~/.codex/config.toml, then export GETAPPNICHE_API_KEY:

toml

[mcp_servers.getappniche]
url = "https://api.getappniche.com/mcp"
bearer_token_env_var = "GETAPPNICHE_API_KEY"

Gemini CLI — ~/.gemini/settings.json (the field is httpUrl):

json

{
  "mcpServers": {
    "getappniche": {
      "httpUrl": "https://api.getappniche.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Zed, Cline, Continue and JetBrains AI are covered too — getappniche.com/mcp has every snippet. Companion agent skills: getappniche/aso-skills (npx skills add getappniche/aso-skills).

ChatGPT — Settings → Connectors → create a custom connector (Developer mode), point it at https://api.getappniche.com/mcp and pick API key authentication, then paste your key.

claude.ai on the web documents request-header auth, but its connector UI currently exposes only OAuth fields — until that settles, use one of the clients above.

What's in this repo

A zero-dependency stdio bridge for clients that speak MCP over stdio and can't send HTTP headers — in two flavours: bin/cli.mjs (Node 18+, published as @getappniche/mcp) and server.py (Python 3.9+, stdlib only). Both forward every JSON-RPC message to the hosted endpoint over TLS and stream responses back.

bash

# Node — one-liner, no install
GETAPPNICHE_API_KEY="getappniche_..." npx -y @getappniche/mcp

# Python — no dependencies
GETAPPNICHE_API_KEY="getappniche_..." python3 server.py

Claude Desktop (claude_desktop_config.json):

json

{
  "mcpServers": {
    "getappniche": {
      "command": "npx",
      "args": ["-y", "@getappniche/mcp"],
      "env": { "GETAPPNICHE_API_KEY": "getappniche_..." }
    }
  }
}

server.json is the manifest published to the official MCP registry as com.getappniche/mcp.

Being ~150 readable lines, it doubles as a reference for what travels over the wire: your API key goes only into the Authorization header of TLS requests to api.getappniche.com — nothing else, nowhere else.

Tools

search_apps - Search apps across 25+ filters: store, categories, languages, price model, rating, reviews, downloads, revenue, release and update recency, review growth - sorted by any column (1 credit)
get_app_detail - Get one app by canonical id, bare Apple id, Android package name, or a pasted store URL (1 credit)
get_app_historicals - Metric time series: reviews, ratings, downloads, revenue (1 credit)
get_keyword_difficulty - Popularity, difficulty, traffic and opportunity for a keyword (10 credits)
batch_keyword_difficulty - Score up to 10 keywords, sorted by opportunity (10 credits per keyword)
get_app_reviews - Live App Store or Google Play reviews for any app by id, package name or URL, or enriched rows for apps monitored in your workspace (1 credit)
get_supported_countries - List valid store country codes (free)

Credits ship with a GetAppNiche plan (Pro: 5,000/month) and every result reports credits_charged. Rate limit: 60 requests/minute per key.

Protocol notes

Methods: initialize → notifications/initialized → tools/list / tools/call. Protocol errors use standard JSON-RPC codes; tool-level errors (bad id, out of credits) come back as tool results your agent can read.
The bridge honours Mcp-Session-Id and accepts both JSON and SSE-framed responses.
OAuth for clients whose connector UI can't set headers (claude.ai web) is in progress; ChatGPT connects today with API-key auth.

License

MIT. Built by GetAppNiche · X @getappniche · LinkedIn

store	any	optional	Limit results to one store: 'apple' (App Store) or 'google' (Google Play). Omit to search both.
category	any	optional	Store category name to filter by, e.g. 'Health & Fitness', 'Productivity', 'Games'. Use 'categories' to include several at once.
categories	any	optional	Several category names to include, e.g. ['Health & Fitness', 'Lifestyle']. Takes precedence over 'category'.
search	any	optional	Free-text query matched against app title and developer name, e.g. 'calorie tracker'.
search_in	any	optional	Which field 'search' matches: 'title', 'developer', or 'all' (default). Use 'developer' to list a publisher's portfolio.
language	any	optional	Single app-language code the listing supports, e.g. 'en', 'de', 'pt-BR'.
languages	any	optional	Several app-language codes to include, e.g. ['en', 'es'].
price_model	any	optional	Monetisation model: 'Free', 'Freemium' or 'Paid'. Case-insensitive on input.
min_rating	any	optional	Lowest average star rating to include, 0-5, e.g. 4.
max_rating	any	optional	Highest average star rating to include, 0-5; use to find weak incumbents.
min_reviews	any	optional	Lowest lifetime review count, e.g. 1000.
max_reviews	any	optional	Highest lifetime review count, e.g. 1000 to exclude entrenched giants.
min_downloads	any	optional	Lowest estimated monthly downloads, e.g. 10000.
max_downloads	any	optional	Highest estimated monthly downloads.
min_revenue	any	optional	Lowest estimated monthly revenue in USD, e.g. 10000 for $10K/month.
max_revenue	any	optional	Highest estimated monthly revenue in USD, e.g. 50000 for $50K/month.
max_days_since_release	any	optional	Only apps first released within this many days, e.g. 90 for fresh launches.
max_days_since_update	any	optional	Only apps updated within this many days, e.g. 30 for actively maintained apps.
released_after	any	optional	Only apps released on or after this date, 'YYYY-MM-DD'.
released_before	any	optional	Only apps released on or before this date, 'YYYY-MM-DD'.
updated_after	any	optional	Only apps last updated on or after this date, 'YYYY-MM-DD'.
updated_before	any	optional	Only apps last updated on or before this date, 'YYYY-MM-DD'.
growth_metric	any	optional	Metric the growth filter measures — currently only 'reviews'.
growth_period	any	optional	Window growth is measured over: '7d', '14d', '30d', '60d' or '90d'. Only '7d' covers Google Play; the longer windows are App Store data, so combining them with store='google' is rejected and leaving the store unset ranks App Store apps only.
growth_direction	any	optional	Keep only apps growing ('up') or declining ('down') over 'growth_period'.
min_growth_pct	any	optional	Lowest absolute growth percentage over 'growth_period', e.g. 20 for at least ±20%.
sort_by	any	optional	Column to sort by: 'downloads' (default), 'revenue', 'growth', 'reviews', 'rating', 'title', 'released' or 'updated'.
sort_dir	any	optional	Sort direction: 'desc' (default, highest first) or 'asc'.
limit	integer	optional	How many apps to return, 1-50 (default 10).
offset	integer	optional	How many apps to skip before returning results; use for paging.

store	string	optional	Which store the store_id belongs to: 'apple' or 'google'.
store_id	string	required	Store-native app id without the store prefix: numeric track id for Apple ('284882215'), bundle id for Google ('com.spotify.music').
days	integer	optional	Length of the history window in days, 7-730 (default 30). Points are daily up to 90 days and weekly beyond that.

keyword	string	required	Search term to score as an ASO target, e.g. 'habit tracker'.
store	string	optional	Store to score against: 'apple' or 'google'.
country	string	optional	Two-letter ISO country code of the storefront, e.g. 'US', 'DE' (default 'US').
language	string	optional	Language code the keyword is written in, e.g. 'en', 'de', 'pt-BR' (default 'en').

keywords	array	required	Up to 10 search terms to score in one call, e.g. ['habit tracker', 'daily planner'].
store	string	optional	Store to score against: 'apple' or 'google'.
country	string	optional	Two-letter ISO country code of the storefront, e.g. 'US', 'DE' (default 'US').
language	string	optional	Language code the keywords are written in, e.g. 'en', 'de' (default 'en').

app_id	any	optional	Any app to read reviews for, whether or not the workspace tracks it. Accepts 'apple:284882215', 'google:com.duolingo', a bare Apple track id, an Android package name, or a store URL. Reviews come straight from the store and carry no sentiment/topic enrichment; Google Play rows have no title.
country	string	optional	Two-letter storefront code the reviews are read from, e.g. 'US', 'DE' (default 'US'). Only applies when 'app_id' is used. For Google Play this also picks the review language of that storefront.
tracked_app_id	any	optional	UUID of one tracked app in the caller's workspace. Omit to read reviews across all tracked apps.
store	any	optional	Filter to reviews from one store: 'apple' or 'google'.
store_id	any	optional	Filter to one app by its store-native id, e.g. '284882215' or 'com.spotify.music'.
sentiment	any	optional	Filter by review sentiment: 'positive', 'neutral' or 'negative'.
topic	any	optional	Filter by an extracted topic label, e.g. 'pricing', 'onboarding', 'bugs'.
limit	integer	optional	How many reviews to return, 1-50 (default 10).
offset	integer	optional	How many reviews to skip before returning results. Live store reads ('app_id' set) reach the 200 newest reviews per app and storefront, so page until 'has_more' is false rather than to a fixed depth; workspace reads page the full stored history.

com.getappniche/mcp

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

search_apps

get_app_detail

get_app_historicals

get_keyword_difficulty

batch_keyword_difficulty

get_app_reviews

get_supported_countries

GetAppNiche MCP — App Store & Google Play intelligence for AI agents

Setup per client

What's in this repo

Tools

Protocol notes

License

Install

Configuration