Scrapling Fetch

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

python

58

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

This MCP server lets your AI assistant fetch text content from websites that use bot protection, bridging the gap between what you can browse and what the AI can access. It is optimized for low-volume retrieval of documentation and reference materials (text/HTML only).

How to use

You use this MCP server by connecting it to your MCP client. When you ask your assistant to fetch or extract information from a web page, the assistant automatically selects the appropriate tool to fetch full pages or to apply regex-based extraction. You can phrase your requests naturally, for example: “Fetch the docs at https://example.com/api,” “Find all mentions of ‘authentication’ on that page,” or “Get the installation instructions from their homepage.” The agent will handle pagination and pattern matching as needed, returning the metadata necessary to decide whether to page further or run a targeted search.

Key capabilities include:

Page fetching: Retrieve complete web pages with support for pagination
Pattern extraction: Find and extract content using regex patterns

How to install

Prerequisites you must have installed before adding this MCP server:

Python 3.10 or newer
uv package manager

Install the MCP server and its browser dependencies with these commands:

Available tools

Page fetching

Retrieves complete web pages with support for pagination to gather long-form content.

Pattern extraction

Finds and extracts specific content using regex patterns on fetched pages.