Fetch MCP

🚀 Get MCP Server

English | 中文

This MCP server provides web content scraping capabilities in various formats, including HTML, JSON, plain text, and Markdown.

✨ Features

Tools

• fetch_html

  • Scrapes website content and returns it in HTML format.
  • Input parameters:
    • url (string, required): The URL of the website to scrape.
    • headers (object, optional): Custom headers to include in the request.
  • Returns the raw HTML content of the web page.

• fetch_json

  • Scrapes a JSON file from a URL.
  • Input parameters:
    • url (string, required): The URL of the JSON to scrape.
    • headers (object, optional): Custom headers to include in the request.
  • Returns the parsed JSON content.

• fetch_txt

  • Scrapes website content and returns it in plain text format (without HTML).
  • Input parameters:
    • url (string, required): The URL of the website to scrape.
    • headers (object, optional): Custom headers to include in the request.
  • Returns the text content of the web page with HTML tags, scripts, and styles removed.

• fetch_markdown

  • Scrapes website content and returns it in Markdown format.
  • Input parameters:
    • url (string, required): The URL of the website to scrape.
    • headers (object, optional): Custom headers to include in the request.
  • Returns the web page content converted to Markdown format.

📦 Installation

Startup Methods

1. Using bun:

bun i
bun start

2. Using docker:

docker compose up --build -d

💻 Usage Examples

Basic Usage

{
  "mcpServers": {
    "fetch-mcp": {
      "transport": "sse",
      "url": "http://localhost:3000/sse",
      "headers": {
        "Authorization": "Bearer your-token-here",
        "X-Custom-Header": "custom-value"
      },
      "useNodeEventSource": true
    }
  }
}

📚 Documentation

Resources

This server does not provide any persistent resources. It is designed to scrape and convert web content on demand.

References

• Original repository zcaceres/fetch-mcp