webclaw

Level ALocal

Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

Overview

webclaw is a fast, local-first web content extraction tool written in Rust that turns websites into clean Markdown, JSON, and LLM-ready context. It offers a CLI, REST API, and MCP server, with scraping, crawling, CSS/XPath selection, table extraction, and screenshots for AI agents and RAG pipelines.

⭐ 2.4kBrowser AutomationRustRepo ↗Updated 2026-11-19

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "webclaw": {
      "command": "npx",
      "args": [
        "-y",
        "@webclaw/mcp"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/0xMassi/webclaw

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "webclaw": {
      "command": "npx",
      "args": [
        "-y",
        "@webclaw/mcp"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers