# MCP Read Website Fast (MCP server)

> MCP Read Website Fast is an MCP server that adds web browsing tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Quickly reads webpages and converts to markdown for fast, token efficient web scraping. It has 163 GitHub stars, is released under the MIT license and runs locally with npx -y @just-every/mcp-read-website-fast.

Fast, token-efficient web content extraction for AI agents - converts websites to clean Markdown. Existing MCP web crawlers are slow and consume large quantities of tokens. This pauses the development process and provides incomplete results as LLMs need to parse whole web pages.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/just-every/mcp-read-website-fast |
| GitHub stars | 163 |
| License | MIT |
| Language | TypeScript |
| Transport | stdio |
| Packages | npm: @just-every/mcp-read-website-fast |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Web & browsing |
| Latest release | none |
| Last commit | Sep 29, 2026 |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp-read-website-fast": {
      "command": "npx",
      "args": [
        "-y",
        "@just-every/mcp-read-website-fast"
      ]
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio mcp-read-website-fast -- npx -y @just-every/mcp-read-website-fast
```

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

```json
{
  "mcpServers": {
    "mcp-read-website-fast": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@just-every/mcp-read-website-fast"
      ]
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

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

```json
{
  "servers": {
    "mcp-read-website-fast": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@just-every/mcp-read-website-fast"
      ]
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Tools

- `read_website`: Fetches a webpage and converts it to clean markdown
- `pages`: Maximum number of pages to crawl (default: 1, max: 100)

## Similar MCP servers

- [Scrapeless MCP Server](https://appsgit.com/mcp-servers/scrapeless-mcp-server): Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents. (169 stars, MIT, needs API key)
- [Free Search](https://appsgit.com/mcp-servers/free-search): No-API-key web search, page fetching and document reading across many engines. (157 stars, MIT)
- [Kreuzcrawl](https://appsgit.com/mcp-servers/kreuzcrawl): Scrape, crawl, and map websites to Markdown or JSON via local CLI. (192 stars, MIT)
- [WebReaper](https://appsgit.com/mcp-servers/webreaper): AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. (152 stars, MIT)
- [CloakBrowser MCP](https://appsgit.com/mcp-servers/cloakbrowser-mcp): Playwright MCP-compatible browser automation bridge for CloakBrowser Chromium. (172 stars, MIT)
- [One Search MCP](https://appsgit.com/mcp-servers/one-search-mcp): Web search, URL discovery, scraping & extraction with agent-browser and search providers. (147 stars, MIT, needs API key)

---

Canonical page: https://appsgit.com/mcp-servers/mcp-read-website-fast
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.