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

• chrome_web_store_extension(id) — full listing for one extension by its 32-character id: name, publisher, rating, rating count, user count, version, last-updated date, category, website, size, languages.
• chrome_web_store_search(query, limit?) — free-text search; matching extensions with id, name, rating, rating count, user count, category, website. A product-led-growth / adoption signal — what people are actually installing.
• chrome_web_store_by_publisher(publisher, max_checked?) — extensions attributed to one publisher name, confirmed against each candidate's own listing. See "Known limits" below — this is bounded, not exhaustive.

Auth

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

Data sources

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

Known limits

• No public "list a developer's extensions" page exists. _by_publisher 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.
• Not-found is a parse condition, not an HTTP status. An id with no live listing still answers HTTP 200 (Google redirects to a canonical empty-title slug with no matching data) — chrome_web_store_extension treats "no data item matches the requested id" as the not-found signal and returns found: false, never a silently-empty success.
• The slug in a detail URL is cosmetic. /detail/<anything>/<id> 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.
• Field extraction reads Google's embedded page data, not a documented 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 upstream_parse error — naming the URL and body length — if a match is found but every field comes back empty, instead of returning an empty success.

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

tools/list at https://gateway.pipeworx.io/chrome-web-store/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1807+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/chrome_web_store_extension \
  -H 'Content-Type: application/json' \
  -d '{"id":"kbfnbcaeplbcioakkpcpgfkobkghlhen"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/chrome_web_store_extension. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "chrome-web-store": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-chrome-web-store"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-chrome-web-store

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Chrome Web Store data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT