Scrapling Fetch MCP

What is Scrapling Fetch MCP?

Scrapling Fetch MCP helps AI assistants fetch content from bot-protected websites. It uses Scrapling (patchright + curl-cffi) to bypass anti-automation measures, returning clean HTML or Markdown. It is optimized for low-volume retrieval of documentation and reference materials.

How to use Scrapling Fetch MCP?

The easiest way is as a Claude Code skill: clone the repository, copy the skills/s-fetch folder into your project’s .claude/skills/ (or ~/.claude/skills/ for all projects), then invoke /s-fetch. For Claude Desktop, install the tool with uv tool install git+https://github.com/cyberchitta/scrapling-fetch-mcp, then add the scrapling-fetch MCP server configuration to your claude_desktop_config.json.

Key features of Scrapling Fetch MCP

• Page fetching with pagination support
• Pattern extraction using regular expressions
• Three automatic protection levels: basic, stealth, max-stealth
• Text-only content (HTML / Markdown output)
• Optimized for low-volume retrieval of documentation

Use cases of Scrapling Fetch MCP

• Fetching docs from bot-protected reference sites
• Extracting specific mentions (e.g., “authentication”) from a page
• Retrieving installation instructions from a protected homepage
• Getting clean Markdown from JavaScript-heavy documentation pages

FAQ from Scrapling Fetch MCP

What does Scrapling Fetch MCP do?

It fetches content from bot-protected websites using anti-automation bypass techniques, returning clean HTML or Markdown to AI assistants.

How do I install Scrapling Fetch MCP as a Claude Code skill?

Clone the repository, copy the skills/s-fetch folder into your project’s .claude/skills/ (or ~/.claude/skills/ for all projects), then invoke /s-fetch to run the one-time setup.

How do I set up Scrapling Fetch MCP for Claude Desktop?

First install the tool with uv tool install git+https://github.com/cyberchitta/scrapling-fetch-mcp. Then add the scrapling-fetch server configuration to your claude_desktop_config.json and restart Claude Desktop.

What are the protection levels?

Three levels: basic (fast, 1–2s), stealth (moderate, 3–8s, headless Chromium), and max-stealth (thorough, 10s+, full browser fingerprint). Escalation is automatic.

What are the limitations of Scrapling Fetch MCP?

It handles text content only (documentation, articles, references). It is not designed for high-volume scraping or sites requiring authentication. Performance varies by site complexity and protection level.