# Website to Markdown

> Website to Markdown is a paid MCP server for web search and scraping. Converts web pages or whole sites to LLM-ready Markdown for RAG pipelines and AI agents. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, CLI, Web
- **Website:** https://apify.com/sumitr_mardy/website-to-markdown
- **MCP Registry name:** io.github.sumitrmardy/website-to-markdown
- **Categories:** [web search and scraping](https://ai-powered.com/categories/web-search-and-scraping), [files and documents](https://ai-powered.com/categories/files-and-documents)
- **Listing updated:** 2026-11-19

## About

The Apify-hosted actor fetches a URL, strips menus, ads, cookie banners and scripts, and returns the main body as Markdown with absolute links and the page title as the first heading. Each result also carries title, description, language, canonical URL, author and publish date, which helps when building retrieval indexes.

The Model Context Protocol endpoint exposes this actor to MCP clients such as Claude, Cursor and VS Code, so an agent can request a page conversion on demand. Crawl mode follows same-host links breadth-first up to a set page and depth limit, and robots.txt is respected by default.

The README is open about limits: there is no JavaScript rendering, so client-built pages often come back nearly empty, and some large publishers block automated requests. Billing is per page converted, with failed, empty and blocked pages not charged.

## Features

- **Main content extraction:** Keeps headings, paragraphs, lists, tables, links and code blocks while dropping page chrome.
- **Whole-site crawling:** Follows links on the start host breadth-first, bounded by a maximum page count and link depth.
- **Page metadata:** Returns title, description, language, canonical URL, author and publish date from meta tags.
- **Robots.txt compliance:** Skips pages disallowed by a site's robots.txt, enabled by default.
- **MCP access:** Exposes the actor through a streamable HTTP MCP endpoint for AI clients.

## Good for

- Preparing documentation sites as chunks for a RAG vector database
- Feeding article text into an LLM prompt without navigation noise
- Mirroring a docs section into local Markdown files
- Letting an AI agent fetch and read a web page as clean text

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http website-to-markdown 'https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown'
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "website-to-markdown": {
      "url": "https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "website-to-markdown": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "website-to-markdown": {
      "serverUrl": "https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown
```

Enter a Name (for example "Website to Markdown"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for a bearer token. Add it under HTTP headers as Authorization: Bearer <your token>.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "website-to-markdown": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown"
    }
  }
}
```

## FAQ

### Does it follow links to other domains?

No, crawling stays on the start URL's host.

### Does it render JavaScript?

No. Pages that build their content in the browser return little text and are marked empty.

### Does it respect robots.txt?

Yes, it is on by default and skips pages the site disallows.

### How is it priced?

$0.50 per 1,000 pages converted; pages with a status other than ok are free.

### Is Website to Markdown free?

No. Website to Markdown is a paid product.

### How do I add Website to Markdown to Claude Code?

Run this command in your terminal: claude mcp add --transport http website-to-markdown 'https://mcp.apify.com/?tools=sumitr_mardy/website-to-markdown'

### What are the best alternatives to Website to Markdown?

The closest alternatives to Website to Markdown are URL to Clean Markdown for LLMs & RAG, URL to Markdown — Clean Page Text, Selectors & Source Links, Website RAG Markdown Crawler & Contact Finder MCP, URL to Markdown Converter and Web to Text (Apify) by Dataset Works.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Status: checked automatically by AIPoweredBot on 20 November 2026.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [URL to Clean Markdown for LLMs & RAG](https://ai-powered.com/mcp/url-to-clean-markdown-for-llms-and-rag): URL to Clean Markdown for LLMs & RAG is a paid MCP server for files and documents.
- [URL to Markdown — Clean Page Text, Selectors & Source Links](https://ai-powered.com/mcp/url-to-markdown-clean-page-text-selectors-and-source-links): URL to Markdown — Clean Page Text, Selectors & Source Links is a paid MCP server for files and documents.
- [Website RAG Markdown Crawler & Contact Finder MCP](https://ai-powered.com/mcp/website-rag-markdown-crawler-and-contact-finder-mcp): Website RAG Markdown Crawler & Contact Finder MCP is a freemium MCP server for web search and scraping.
- [URL to Markdown Converter](https://ai-powered.com/mcp/url-to-markdown-converter): URL to Markdown Converter is a paid MCP server for files and documents.
- [Web to Text (Apify) by Dataset Works](https://ai-powered.com/mcp/web-to-text-apify-by-dataset-works): Web to Text (Apify) by Dataset Works is a paid MCP server for web search and scraping.
- [Website to Markdown Crawler](https://ai-powered.com/mcp/website-to-markdown-crawler): Website to Markdown Crawler is a paid MCP server for web search and scraping.
- [Web Scraper & Crawler for RAG (Markdown)](https://ai-powered.com/mcp/web-scraper-and-crawler-for-rag-markdown): Web Scraper & Crawler for RAG (Markdown) is a paid MCP server for web search and scraping.
- [Docsieve: Website to Markdown for RAG](https://ai-powered.com/mcp/docsieve-website-to-markdown-for-rag): Docsieve: Website to Markdown for RAG is a paid MCP server for files and documents.

---
Source: https://ai-powered.com/mcp/website-to-markdown-2
