Markgrab
Universal web content extraction — convert any URL to clean, LLM-ready markdown. Supports HTML pages (with content density filtering and auto-fallback to Playwright for JS-heavy sites), YouTube transcripts, PDF, and DOCX. Provides both MCP tools (extracturl, extractmultiple) for automatic invocation and skills for manual use. Built on httpx and BeautifulSoup, with optional Playwright browser rendering. Available on PyPI: pip install markgrab
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Productivity — see all ranked ›
- tashan score: 27.0
- Adoption: 1 repos
- Health: active
- GitHub stars: 0
- Contributors: 1
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:quartzunit/markgrab-plugin/markgrab
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›