apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-04-25 00:06:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
webclaw/packages/create-webclaw
History
Valerio c99ec684fa Initial release: webclaw v0.1.0 — web content extraction for LLMs 
CLI + MCP server for extracting clean, structured content from any URL.
6 Rust crates, 10 MCP tools, TLS fingerprinting, 5 output formats.

MIT Licensed | https://webclaw.io
2026-03-23 18:31:11 +01:00
..
index.mjs Initial release: webclaw v0.1.0 — web content extraction for LLMs 2026-03-23 18:31:11 +01:00
package.json Initial release: webclaw v0.1.0 — web content extraction for LLMs 2026-03-23 18:31:11 +01:00
README.md Initial release: webclaw v0.1.0 — web content extraction for LLMs 2026-03-23 18:31:11 +01:00

README.md

create-webclaw

Set up webclaw MCP server for AI agents in one command.

Usage

npx create-webclaw

What it does

  1. Detects installed AI tools (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code + Continue)
  2. Downloads the webclaw-mcp binary for your platform
  3. Asks for your API key (optional — works locally without one)
  4. Configures MCP in each detected tool

Supported tools

Tool Config location
Claude Desktop ~/Library/Application Support/Claude/claude_desktop_config.json
Claude Code ~/.claude.json
Cursor .cursor/mcp.json
Windsurf ~/.codeium/windsurf/mcp_config.json
VS Code (Continue) ~/.continue/config.json

MCP tools provided

After setup, your AI agent has access to:

  • scrape — extract content from any URL
  • crawl — recursively crawl a website
  • search — web search + parallel scrape
  • map — discover URLs from sitemaps
  • batch — extract multiple URLs in parallel
  • extract — LLM-powered structured extraction
  • summarize — content summarization
  • diff — track content changes
  • brand — extract brand identity