Skip to content
Back to search

scrapling-fetch-mcp

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/cyberchitta/scrapling-fetch-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/cyberchitta/scrapling-fetch-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/cyberchitta--scrapling-fetch-mcp/badge.svg)](/listings/cyberchitta--scrapling-fetch-mcp)

HTML

<a href="/listings/cyberchitta--scrapling-fetch-mcp"><img src="/api/listings/cyberchitta--scrapling-fetch-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 95 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # scrapling-fetch-mcp
  2. [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
  3. [![PyPI version](https://img.shields.io/pypi/v/scrapling-fetch-mcp.svg)](https://pypi.org/project/scrapling-fetch-mcp/)
  4. Helps AI assistants fetch content from bot-protected websites. Uses Scrapling (patchright + curl-cffi) to bypass anti-automation measures, returning clean HTML or Markdown.
  5. > Optimized for low-volume retrieval of documentation and reference materials. Not designed for high-volume scraping or data harvesting.
  6. **Requirements**: Python 3.10+, [uv](https://github.com/astral-sh/uv)
  7. ## Claude Code Skill
  8. 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.
  9. **Install into your project** (recommended — only loads in this project's context):
  10. ```bash
  11. git clone --depth=1 https://github.com/cyberchitta/scrapling-fetch-mcp /tmp/scrapling-fetch-mcp
  12. cp -r /tmp/scrapling-fetch-mcp/skills/s-fetch .claude/skills/
  13. rm -rf /tmp/scrapling-fetch-mcp
  14. ```
  15. **Or install for all projects** (loads into context everywhere):
  16. ```bash
  17. git clone --depth=1 https://github.com/cyberchitta/scrapling-fetch-mcp /tmp/scrapling-fetch-mcp
  18. cp -r /tmp/scrapling-fetch-mcp/skills/s-fetch ~/.claude/skills/
  19. rm -rf /tmp/scrapling-fetch-mcp
  20. ```
  21. The first time you invoke `/s-fetch`, Claude will read
  22. `skills/s-fetch/references/install.md` and run the one-time setup
  23. (installs the tool and downloads browser binaries). After that, just
  24. ask naturally:
  25. ```
  26. "Fetch the docs at https://example.com/api"
  27. "Find all mentions of 'authentication' on that page"
  28. "Get me the installation instructions from their homepage"
  29. ```
  30. ## Claude Desktop (MCP Server)
  31. If the `/s-fetch` skill has already installed the tool, skip to the config below.
  32. Otherwise install first:
  33. ```bash
  34. uv tool install git+https://github.com/cyberchitta/scrapling-fetch-mcp
  35. uvx --from git+https://github.com/cyberchitta/scrapling-fetch-mcp scrapling install
  36. ```
  37. > **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.
  38. > **Upgrading**: after `uv tool upgrade scrapling-fetch-mcp`, re-run the `scrapling install` line above. A new Scrapling release can need newer browser binaries, and until they are installed the `stealth` and `max-stealth` modes fail with `Executable doesn't exist`.
  39. Add this to your Claude Desktop MCP settings and restart:
  40. **MacOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
  41. **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
  42. ```json
  43. {
  44. "mcpServers": {
  45. "scrapling-fetch": {
  46. "command": "uvx",
  47. "args": ["scrapling-fetch-mcp"]
  48. }
  49. }
  50. }
  51. ```
  52. ## How It Works
  53. Two tools, used automatically by Claude:
  54. - **Page fetching** — retrieves complete pages with pagination support
  55. - **Pattern extraction** — finds content matching a regex
  56. Three protection levels, escalated automatically:
  57. - **basic** — fast (1-2s), works for most sites
  58. - **stealth** — moderate (3-8s), headless Chromium
  59. - **max-stealth** — thorough (10s+), full browser fingerprint
  60. ## Limitations
  61. - Text content only (documentation, articles, references)
  62. - Not for high-volume scraping or sites requiring authentication
  63. - Performance varies by site complexity and protection level
  64. ## License
  65. Apache 2.0

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.