Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@clean-markdown-mcp scrape https://en.wikipedia.org/wiki/Markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that turns any URL into clean, LLM-ready Markdown — no ads, no nav bars, no cookie banners, no scripts.
Built for RAG pipelines and AI agents, where junk in the input means junk in the output.
Give it: https://en.wikipedia.org/wiki/Markdown
Get back: # Markdown
Markdown is a lightweight markup language for creating
formatted text using a plain-text editor...npm install -g clean-markdown-mcpRelated MCP server: urltomarkdown-mcp
Add this to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"clean-markdown": {
"command": "npx",
"args": ["-y", "clean-markdown-mcp"]
}
}
}Restart Claude Desktop, then ask it to "scrape https://example.com to Markdown."
Works the same way in Cursor, Windsurf, or any other MCP client — point it at the
clean-markdown-mcp command.
scrape_url
Parameter | Type | Description |
| string | The page to scrape. Must be |
| boolean | Keep hyperlinks in the Markdown. Default |
| boolean | Load the page in a real browser first, for JavaScript-built sites. Default |
Returns the page title, source, word count, and the clean Markdown.
Fetch — with a 20-second timeout, a 5 MB size cap, and redirects validated at every hop.
Clean — runs Mozilla Readability, the engine behind Firefox Reader View, to isolate the real article and discard navigation, sidebars, ads, and comment sections.
Convert — Turndown renders it as GitHub-flavoured Markdown, preserving headings, lists, tables, and code blocks.
If a page isn't article-shaped, it falls back to a cleaned <body> rather than
failing, so you still get usable text.
Some sites build their content with JavaScript after loading. A plain fetch returns almost nothing for those. To handle them, install Playwright once:
npm install playwright && npx playwright install chromiumThen pass renderJs: true. The difference on such a page is dramatic:
Mode | Result |
Default | ~3 words — just navigation links |
| ~190 words — the full content |
Playwright is not a dependency of this package, so a normal install stays
small and fast. Without it, renderJs returns a clear message telling you how to
enable it.
The scraper refuses private, loopback, and link-local addresses — including cloud
metadata endpoints like 169.254.169.254 — and re-validates every redirect hop.
This matters because an MCP server runs on your machine, with access to your
local network.
This package handles one page at a time, locally. For batch scraping, hosted JavaScript rendering, and a pay-per-page API with no infrastructure to run, the same engine is available as a hosted Actor:
https://apify.com/perforated_hummingbird/url-to-markdown
Some sites block automated traffic. That's a site policy, not a bug here.
Non-UTF-8 pages may render with garbled characters.
No robots.txt enforcement — you are responsible for how you use it.
npm install
npm run build
node dist/try.js https://example.com # quick test
node dist/try.js https://example.com --render # with JS renderingMIT
Fetch any web page and return its main content as clean, readable Markdown. Strips out navigation, ads, cookie banners, scripts, and other boilerplate. Ideal for feeding article or documentation content to an LLM.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The full URL of the web page to scrape (must start with http:// or https://). | |
| renderJs | No | Render the page in a real browser first (default false). Use for sites whose content is built by JavaScript. Requires Playwright to be installed. | |
| includeLinks | No | Keep hyperlinks in the output (default true). Set to false for cleaner plain prose. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are present, the description carries the full burden. It discloses that the tool strips navigation, ads, cookie banners, scripts, and other boilerplate, and outputs clean Markdown. This gives the agent meaningful behavioral expectations, though it does not cover error handling or rate limits, which would be desirable but not essential for this tool type.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core functionality, and contains no fluff. It efficiently conveys the behavior and use case.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the fully documented schema, the description covers the essential context. It clarifies the return format (Markdown) and the cleaning behavior, which is important because there is no output schema. The description is complete for this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents each parameter. The description adds no extra meaning beyond what the schema provides for url, renderJs, and includeLinks. The baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear verb-resource pair: 'Fetch any web page and return its main content as clean, readable Markdown.' It also specifies the cleanup behavior, making the tool's purpose unmistakable. No sibling tools exist, so no differentiation is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear usage context: 'Ideal for feeding article or documentation content to an LLM.' It implies the tool is for extracting clean main content, but does not explicitly mention when not to use it or list alternatives (none exist). The use case guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.1.3scrape_urlWith only a single tool, there is no possibility of confusion or overlap. The tool's purpose is clear and distinct by definition.
The tool name 'scrape_url' follows a clear verb_noun pattern, which is consistent with common MCP naming conventions. With only one tool, the pattern is trivially consistent.
The server has only 1 tool, which is below the typical 3-15 range. However, it is appropriately scoped for a highly focused purpose: fetching and converting web pages to clean markdown. The single tool fully covers the server's stated function.
The domain is 'clean-markdown', and the single tool provides a complete lifecycle: it fetches any web page and returns clean markdown, covering all necessary functionality. There are no obvious gaps for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Converts any URL to clean, LLM-ready Markdown using real Chrome browsers
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Fetch any URL and get clean Markdown. Web scraping for AI agents.
URL to clean markdown for LLMs: a polite, robots.txt-respecting web reader. Free, no API key
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/damonwill78-a11y/clean-markdown-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
