Burnworks MCP Server Fetch

🚀 MCP Server with CSS Selector Functionality for fetch()

This is a Model Context Protocol (MCP) server that provides the ability to fetch web page content from the internet. This server enables Large Language Models (LLMs) to retrieve and process web page content, converting HTML into Markdown format for easier reading.

The fetch tool truncates the response, but by using the start_index parameter, you can specify where to start extracting content. This allows the model to read the web page in chunks until it finds the required information.

✨ Features

Available Tools

• custom-fetch: Fetches a URL from the internet and converts its content to Markdown format.
  • url (string, required): The URL to fetch.
  • max_length (integer, optional): The maximum number of characters to return (default: 5000).
  • start_index (integer, optional): The character index from which to start extracting content (default: 0).
  • raw (boolean, optional): Fetch the raw content without Markdown conversion (default: false).
  • selector (string, optional): A selector for filtering content.
  • selector_type (string, optional): The type of the selector, supporting three types: element, id, and css.

📦 Installation

You can install this server using the following commands:

Install with pip

pip install burnworks_mcp_server_fetch

Install with uvx (Recommended)

uvx add https://github.com/your-repo/burnworks_mcp_server_fetch.git

Configuration

Add the following configuration to the package.json file to enable the MCP server:

{
  "mcp": {
    "servers": {
      "fetch": {
        "path": "node_modules/burnworks_mcp_server_fetch/out",
        "cliOptions": {
          "--custom-fetch": {
            "url": "https://example.com",
            "selector": ".content",
            "selector_type": "css"
          }
        }
      }
    }
  }
}

💻 Usage Examples

Extract the main content area

custom-fetch
  url: https://example.com/article
  selector: main
  selector_type: element

Extract content by ID

custom-fetch
  url: https://example.com/blog
  selector: article-body
  selector_type: id

Extract content using a complex CSS selector

custom-fetch
  url: https://example.com/documentation
  selector: .content-wrapper article > section:first-child
  selector_type: css

Contribution

This project burnworks_mcp_server_fetch is a fork of the original MCP server, with the addition of CSS selector functionality. If you wish to contribute to the enhanced version, please visit our repository to submit issues or pull requests.

📄 License

This project is released under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms of the MIT License. For more details, please refer to the LICENSE file in the project repository.