App Store Review Analysis with AI

The fastest product research there is: read what real users hate about an app. toolkb pulls recent App Store reviews with a rating histogram, so your AI can group complaints and spot the gap you can fill.

Claude CodeCodexCursorNo API keyMIT licensed
View on GitHub →

Install in one line

Claude Code

claude mcp add toolkb -- npx -y github:jack-reson8/toolkb-mcp

Codex (~/.codex/config.toml)

[mcp_servers.toolkb]
command = "npx"
args = ["-y", "github:jack-reson8/toolkb-mcp"]

Cursor, Claude Desktop, Windsurf (mcp.json)

{ "mcpServers": { "toolkb": { "command": "npx", "args": ["-y", "github:jack-reson8/toolkb-mcp"] } } }

Needs Node.js 18+. Runs locally, no API key, no account. Behind a proxy? HTTPS_PROXY is picked up automatically.

What your assistant gets

# App Store reviews: Notion: Notes, Tasks, AI

- All-time rating: 4.78 from 90,424 ratings
- Recent sample: 100 reviews, average 2.66 (5★ 28, 4★ 4, 3★ 14, 2★ 14, 1★ 40)

### ★☆☆☆☆ Unintuitive bloat
2026-10-14 · v1.7.346
One of the most unintuitive apps I've ever used…

Things to ask

Also included

The same server gives your assistant YouTube transcripts, whole playlists and channels, web pages as Markdown and App Store reviews. There is also a terminal command: npx -y -p github:jack-reson8/toolkb-mcp toolkb yt <url>.

FAQ

Where do the reviews come from?

Apple's official public customer-reviews feed: up to 10 pages of 50 reviews per country store, newest first.

Can I choose the country?

Yes, any two-letter App Store country code (us, gb, jp, cn…).

Google Play?

Not yet – Google offers no public review feed; it is on the roadmap.

Is it free?

Yes. The MCP server and CLI are open source and run on your computer.

More from ToolKB