scraper-mcp

Akitaroh/scraper-mcp

★ 0 stars TypeScript 🌐 Browser/Web Updated today

MCP server (and Node library) that fetches JS-rendered web pages with Playwright. Cloudflare-aware, cacheable, rate-limited, with built-in SSRF guard.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "scraper-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "Akitaroh/scraper-mcp"
      ]
    }
  }
}

README Excerpt

> An MCP server (and Node library) that fetches **JS-rendered web pages** with Playwright. Designed to be used from Claude Code or any MCP-aware client when a plain HTTP fetch returns an empty SPA shell. --- The web has moved to client-rendered apps. `curl https://...` against a React, Vue, or Salesforce community page often returns an HTML shell with `<div id="root"></div>` and no actual content. You need a real browser to see what humans see.

Tools (18)

contentdurationMsextraHTTPHeadersformatfromCacheheadfullaunchArgslocalenetworkidleoutputrateLimitMsrawPathtimeoutundefinedurluserAgentwaitForwaitForCloudflare

scraper-mcp

Quick Install

README Excerpt

Tools (18)

Related Browser/Web Servers