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.
- tool
- 1
- transport
- STDIO
- last updated
- Apr 27, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
fetch_url_as_markdownFetches a URL and returns the main content as clean Markdown.
Fetches a URL and returns the main content as clean Markdown.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
web-to-markdown-mcp
An MCP server that fetches a URL and returns the main content as clean Markdown. Uses plain HTTP when possible and real Chromium when needed.
Why
Most MCP web-fetch tools either:
- use plain HTTP, which fails on JS-required pages and gets blocked by Cloudflare bot detection on many sites; or
- use a real browser but return raw HTML or accessibility-tree snapshots, which are noisy and token-heavy when you just want to read the article.
This server uses a three-tier strategy, using the fastest approach that works for each URL:
- Native markdown fast-path. Every request first tries a plain HTTP GET with an
Accept: text/markdownheader. Servers that support content negotiation — such as Cloudflare-hosted sites with Markdown for Agents enabled — respond withContent-Type: text/markdown, and the body is returned immediately with no browser overhead.
Details
- Repository
- github.com/sidney/web-to-markdown-mcp
- Categories
- Web & Browser Automation, Documents & Knowledge
- Package
web-to-markdown-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related Web & Browser Automation MCP servers
View all
Flakiness Knowledge Graph Mcpvola-trebla/flakiness-knowledge-graph-mcpMCP server + Playwright reporter that builds a flakiness knowledge graph from test run history0stars
Next AI Draw.iodayuanjiang/next-ai-draw-iodraw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand36.9Kstars
Spree Commerce developer docs for AI agentsspree/spreeSpree Commerce docs for AI coding agents: build headless B2B and marketplace ecommerce on its APIs.15.8Kstars
Actionbookactionbook/actionbookLet your AI agent operate any website through a real, logged-in browser session.1.6Kstars
Unbrowseunbrowse-ai/unbrowseWebsites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.904stars
FableCutronak-create/fablecutZero-dependency browser video editor AI agents drive via a JSON timeline over MCP; ffmpeg export.780stars