Chrome Web Store MCP server

@pipeworx/chrome-web-store

Chrome Web Store listing data: one extension by id, free-text search, and extensions attributed to one publisher — name, rating, user count, version, last-updated date, category and website for each.

Part of Pipeworx — an MCP gateway connecting AI agents to 1807+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

32-character id: name, publisher, rating, rating count, user count, version, last-updated date, category, website, size, languages.

• chromewebstore_extension(id) — full listing for one extension by its

extensions with id, name, rating, rating count, user count, category, website. A product-led-growth / adoption signal — what people are actually installing.

• chromewebstore_search(query, limit?) — free-text search; matching

attributed to one publisher name, confirmed against each candidate's own listing. See "Known limits" below — this is bounded, not exhaustive.

• chromewebstorebypublisher(publisher, max_checked?) — extensions

Auth

Keyless. No login, no API key — this reads the same public pages a browser does.

Data sources

public read API: Google's own Chrome Web Store API only manages the caller's OWN published items (OAuth, developer-scoped) and cannot look up someone else's extension, so this pack reads the public pages the same way a browser would.

• Google, Chrome Web Store public listing and search pages. There is no

Known limits

runs the publisher name through the public search, then opens each candidate's own listing and keeps only the ones whose rendered Developer disclosure actually names that publisher. That is an approximation of "all" bounded by what Chrome Web Store's own search surfaces for that query — not a guaranteed-complete catalog of everything a publisher has shipped. It also makes one extra HTTP call per candidate checked (max_checked, default 10, max 25), so keep it modest.

• No public "list a developer's extensions" page exists. bypublisher

listing still answers HTTP 200 (Google redirects to a canonical empty-title slug with no matching data) — chromewebstore_extension treats "no data item matches the requested id" as the not-found signal and returns found: false, never a silently-empty success.

• Not-found is a parse condition, not an HTTP status. An id with no live

redirects to the real canonical slug server-side regardless of what precedes the id, so this pack never needs to know an extension's display slug — only its id.

• The slug in a detail URL is cosmetic. /detail//

API, so a Chrome Web Store redesign could change the shape. The pack detects that defensively: it walks the page's embedded JSON for an array whose first element is a 32-character extension id (Chrome's own id alphabet, a-p only) rather than assuming a fixed block number, and it raises a loud upstreamparse error — naming the URL and body length — if a match is found but every field comes back empty, instead of returning an empty success.

• **Field extraction reads Google's embedded page data, not a documented

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "chrome-web-store": {
      "url": "https://gateway.pipeworx.io/chrome-web-store/mcp"
    }
  }
}

What this endpoint actually serves

Shortened. The full README is on GitHub.