mcpbeat

Getappniche MCP Server

com.getappniche/mcp
answering

Getappniche is answering right now. Last checked 3 min ago. 245 installs a week from npm. It exposes 7 tools. Last commit 31 Jul 2026.

Live App Store & Google Play data for AI agents: app discovery, ASO keywords, reviews.

Installs per day peak 160 · avg 12 · +71% w/w
a month agotoday
Uptime history 44 hours of history
44 hours agonow
100.0%
Uptime 24h
91 of 91 checks
7
Tools
read from the server
592 ms
Response time
average over 24h
245
Installs / week
npm and PyPI

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

run in your terminal
claude mcp add mcp --transport http https://api.getappniche.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.getappniche.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://api.getappniche.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.getappniche.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.getappniche.com/mcp"
    }
  }
}

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

app
get_app_detail
Return one app's full record. Accepts the canonical id ("apple:284882215", "google:com.spotify.music"), a bare Apple track id, an Android package name, or a pasted App Store / Google Play URL. Cost: 1 credit.
get_app_historicals
Return historical metric points for one app (daily up to 90 days, weekly beyond). Cost: 1 credit.
get_app_reviews
Read app reviews two ways: pass app_id for live store reviews of ANY app — App Store or Google Play — (no tracking needed, storefront selectable), or omit it to read the workspace's tracked apps with sentiment, topics and improvement areas attached. Live Google Play rows carry no title (Play reviews have none). Cost: 1 credit.
apps
search_apps
Search App Store and Google Play apps across 25+ filters — store, category, language, price model, rating, review count, download and revenue estimates (min and max), release and update recency, and review-growth direction — sorted by any column. The tool behind niche sizing and competitor shortlists. Cost: 1 credit.
batch
batch_keyword_difficulty
Score up to 10 keywords in one call. Cost: 10 credits per keyword.
keyword
get_keyword_difficulty
Score one keyword for difficulty and opportunity, on the App Store or Google Play. Cost: 10 credits.
supported
get_supported_countries
Return supported country codes. Cost: free.

Endpoints

URLTransportStateLatencyChecked
https://api.getappniche.com/mcp streamable-http answering 632 ms 3 min ago

Getappniche — questions

Answers built from our own checks of this server.

What can Getappniche do?
It exposes 7 tools, read directly from the server on our last check. Among them: batch_keyword_difficulty, get_app_detail, get_app_historicals, get_app_reviews, get_keyword_difficulty, get_supported_countries and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Getappniche working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 592 ms. The bar chart above shows every period we have measured.
How do I connect Getappniche?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Getappniche need an API key?
No. Getappniche completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Getappniche?
It answers our handshake in 592 ms on average, which is faster than 17% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Getappniche?
The npm package @getappniche/mcp was installed 245 times in the last week. Week over week that is +71%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Getappniche open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.