{"slug":"0xmassi/webclaw","name":"Webclaw","description":"Web content extraction for LLM pipelines — clean markdown or structured JSON from any URL using browser-grade TLS fingerprinting, no headless browser required. CLI, REST API, and MCP server.","category":"web-scraping","tags":[],"official":false,"stars":1192,"transport":null,"install":[{"cmd":"npx create-webclaw","imports":[]}],"tools":[{"name":"scrape","description":"Extract one URL as markdown, text, JSON, LLM format, or HTML"},{"name":"crawl","description":"Follow same-origin links and extract discovered pages"},{"name":"map","description":"Discover URLs without extracting every page"},{"name":"batch","description":"Scrape multiple URLs in parallel"},{"name":"extract","description":"Convert page content into structured data"},{"name":"summarize","description":"Summarize a page"},{"name":"diff","description":"Compare page content snapshots"},{"name":"brand","description":"Extract colors, fonts, logos, and metadata"},{"name":"search","description":"Search the web and scrape results"},{"name":"research","description":"Multi-source research workflow"}],"env_vars":["WEBCLAW_API_KEY","OLLAMA_HOST","OPENAI_API_KEY","OPENAI_BASE_URL","ANTHROPIC_API_KEY","ANTHROPIC_BASE_URL"],"auth_type":"none","github":"https://github.com/0xMassi/webclaw","homepage":"","server_url":"","status":"active","source":"mcpservers.org","updated_at":"Mon May 25"}