Skip to main content
Glama
Scrapling Fetch MCP

Scrapling Fetch MCP

by cyberchitta

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"

Related MCP server: mult-fetch-mcp-server

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.

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.

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

{
  "mcpServers": {
    "scrapling-fetch": {
      "command": "uvx",
      "args": ["scrapling-fetch-mcp"]
    }
  }
}

How It Works

Two tools, used automatically by Claude:

  • Page fetching — retrieves complete pages with pagination support

  • Pattern extraction — finds content matching a regex

Three protection levels, escalated automatically:

  • basic — fast (1-2s), works for most sites

  • stealth — moderate (3-8s), headless Chromium

  • max-stealth — thorough (10s+), full browser fingerprint

Limitations

  • Text content only (documentation, articles, references)

  • Not for high-volume scraping or sites requiring authentication

  • Performance varies by site complexity and protection level

License

Apache 2.0

Available Tools

2 tools
s_fetch_pageA

Fetches a complete web page with pagination support. Retrieves content from websites with bot-detection avoidance. For best performance, start with 'basic' mode (fastest), then only escalate to 'stealth' or 'max-stealth' modes if basic mode fails. Content is returned as 'METADATA: {json}\n\n[content]' where metadata includes length information and truncation status.

Args:
    url: URL to fetch
    mode: Fetching mode (basic, stealth, or max-stealth)
    format: Output format (html or markdown)
    max_length: Maximum number of characters to return.
    start_index: On return output starting at this character index, useful if a previous fetch was truncated and more content is required.

Inputs: url (required), mode, format, max_length, +1 more. Returns: result

s_fetch_patternA

Extracts content matching regex patterns from web pages. Retrieves specific content from websites with bot-detection avoidance. For best performance, start with 'basic' mode (fastest), then only escalate to 'stealth' or 'max-stealth' modes if basic mode fails. Returns matched content as 'METADATA: {json}\n\n[content]' where metadata includes match statistics and truncation information. Each matched content chunk is delimited with '॥๛॥' and prefixed with '[Position: start-end]' indicating its byte position in the original document, allowing targeted follow-up requests with s-fetch-page using specific start_index values.

Args:
    url: URL to fetch
    search_pattern: Regular expression pattern to search for in the content
    mode: Fetching mode (basic, stealth, or max-stealth)
    format: Output format (html or markdown)
    max_length: Maximum number of characters to return.
    context_chars: Number of characters to include before and after each match

Inputs: url (required), search_pattern (required), mode, format, +2 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: s_fetch_page retrieves entire web pages with pagination support, while s_fetch_pattern extracts specific content matching regex patterns. Their descriptions explicitly differentiate them, with no overlap in functionality that would cause confusion.

    Naming Consistency5/5

    Both tools follow a consistent 's_fetch_' prefix pattern with descriptive suffixes ('page' and 'pattern'), maintaining perfect naming consistency. The snake_case convention is applied uniformly across both tool names.

    Tool Count3/5

    With only 2 tools, the server feels somewhat thin for a web scraping domain that typically requires more operations like navigation, form handling, or session management. While the tools are well-designed, the limited count may restrict agent capabilities for complex scraping tasks.

    Completeness4/5

    The tools cover the core web scraping operations of fetching pages and extracting patterns with bot-detection avoidance. However, there are notable gaps for a complete scraping workflow, such as no tools for navigating between pages, handling authentication, managing sessions, or interacting with dynamic content beyond basic fetching.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers