Web To Markdown Mcp

Fetches web pages and returns clean Markdown instead of raw HTML or bloated accessibility trees. Tries plain HTTP first, falls back to headless Chromium when needed for JavaScript-heavy sites, and uses visible browser mode as a last resort for aggressive bot detection. Exposes a single fetch_url_as_markdown tool with parameters for navigation timing, timeouts, and content stabilization polling. The headless browser stays alive between requests to avoid repeated startup costs. Built on trafilatura for extraction and patchright for anti-detection. Useful when you need readable article content from sites that block simple HTTP clients or return JavaScript shells, and you want to avoid dumping thousands of tokens of HTML tags into context.