Happy slice of mcp pizzaMCP.pizza

scrapling-fetch-mcp

MCP.Pizza Chef: cyberchitta

Two tools do the work: fetch a whole page, or pull only the parts matching a pattern you describe. Three levels of disguise are on offer, from a quick request up to a full browser fingerprint, and your assistant steps up a level itself when a page refuses, since there is no automatic retry in the code. Only http and https addresses are accepted, a rule that is genuinely enforced, so it cannot be talked into reading files off your disk. No key or account is needed, though the first run downloads several hundred megabytes of browser files.

Coding
Web/Research

Use This MCP server To

Read a documentation page my assistant otherwise cannot open Pull just the install steps out of a very long page Find every mention of a word across a reference page Get an article's text when the site blocks plain requests

README

scrapling-fetch-mcp

License PyPI version

Helps AI assistants fetch content from bot-protected websites. Uses Scrapling (patchright + curl-cffi) to bypass anti-automation measures, returning clean HTML or Markdown.

Optimized for low-volume retrieval of documentation and reference materials. Not designed for high-volume scraping or data harvesting.

Requirements: Python 3.10+, uv

Claude Code Skill

The easiest way to use this is as a Claude Code skill. Once installed, Claude will automatically fetch bot-protected URLs when you ask — no manual commands needed.

Install into your project (recommended — only loads in this project's context):

git clone --depth=1 https://github.com/cyberchitta/scrapling-fetch-mcp /tmp/scrapling-fetch-mcp
cp -r /tmp/scrapling-fetch-mcp/skills/s-fetch .claude/skills/
rm -rf /tmp/scrapling-fetch-mcp

Or install for all projects (loads into context everywhere):

git clone --depth=1 https://github.com/cyberchitta/scrapling-fetch-mcp /tmp/scrapling-fetch-mcp
cp -r /tmp/scrapling-fetch-mcp/skills/s-fetch ~/.claude/skills/
rm -rf /tmp/scrapling-fetch-mcp

The first time you invoke /s-fetch, Claude will read skills/s-fetch/references/install.md and run the one-time setup (installs the tool and downloads browser binaries). After that, just ask naturally:

"Fetch the docs at https://example.com/api"
"Find all mentions of 'authentication' on that page"
"Get me the installation instructions from their homepage"

Claude Desktop (MCP Server)

If the /s-fetch skill has already installed the tool, skip to the config below.

Otherwise install first:

uv tool install git+https://github.com/cyberchitta/scrapling-fetch-mcp
uvx --from git+https://github.com/cyberchitta/scrapling-fetch-mcp scrapling install

Note: Browser installation downloads hundreds of MB and must complete before first use. If the server times out initially, wait a few minutes and try again.

Add this to your Claude Desktop MCP settings and restart:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

scrapling-fetch-mcp FAQ

Do I need a key or an account?
No. There is nothing to sign up for and nothing to pay. Everything runs from your own machine.
Can I use this to read a page that blocks my assistant?
Yes, that is its whole purpose. It fetches the page while looking like an ordinary browser and hands back clean text or markdown.
How hard is setup?
Copy-paste level, with one long wait. You paste a short block into your settings, but the first run downloads several hundred megabytes of browser files and may time out before finishing. Try again a few minutes later.
Can it read files on my computer?
No. It accepts only http and https web addresses, and that rule is properly enforced in the code rather than merely promised in the README.
Will it get me past a login?
No. The author is explicit that it is not for sites requiring sign-in, and that it is built for occasional reading of documentation rather than bulk collection.
Does it really escalate through the three modes by itself?
Not in the code. Your assistant is told to start on the fastest setting and try a stronger one if the page refuses, so the stepping up is a decision it makes, not an automatic retry.
Which apps does it work in?
Claude Desktop is documented, and it works in anything that can start a local command. There is also a Claude Code skill version that handles the install for you.
Should I think about the site's rules?
Yes, worth a moment. It exists to get past measures a site put up deliberately, so check the terms before using it on anything beyond public documentation.
Is it maintained?
Yes. The code changed in August 2026, there are no open issues, and it carries a clear Apache licence, so workplace use is straightforward.