Skip to content
Grok

scraper for Grok

io.github.ofershap/scraper

Web scraping MCP — extract clean markdown, links, and metadata from any URL.

client:Grok transport:stdio runtime:npm

Install scraper in Grok

.mcp.json (in your project root)

{
  "mcpServers": {
    "scraper": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-scraper"
      ]
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

scraper in other clients