# Read Website Fast

> Use this tool when you need to quickly extract web content and convert it to clean Markdown format for research, documentation, or content analysis. It solves problems of slow and cumbersome web content processing, providing fast and intelligent article detection and HTML-to-Markdown conversion. With inputs of website URLs and outputs of Markdown-formatted content, it is ideal for AI assistants requiring efficient web content extraction and processing.

Canonical page: https://skillsregistry.net/skills/just-every-read-website-fast  
JSON: https://api.skillsregistry.net/v1/skills/just-every-read-website-fast

## Description

This MCP server provides fast web content extraction and conversion to clean Markdown format, built by Just Every using TypeScript with Mozilla Readability for intelligent article detection and Turndown for HTML-to-Markdown conversion. It features disk-based caching, robots.txt compliance, concurrent crawling with configurable depth, and both CLI and MCP server modes for flexible integration. The implementation uses JSDOM for DOM parsing, supports relative URL conversion to absolute URLs, and includes smart content detection that applies Readability extraction only to clear article/blog pages while preserving full page content for other types of websites. Valuable for AI assistants that need to quickly extract and process web content for research, documentation, or content analysis workflows where clean Markdown output and fast performance are priorities.

## Trust

- **Trust score (0–1):** 0.76
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/just-every-read-website-fast)
- **Repository:** <https://github.com/just-every/mcp-read-website-fast>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "just-every-read-website-fast"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/just-every-read-website-fast` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/just-every-read-website-fast/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt