fetcher-mcp

Level ALocal

MCP server for fetch web page content using Playwright headless browser.

Overview

Fetcher MCP is an MCP server that fetches web page content using a Playwright headless browser. It executes JavaScript to handle dynamic pages and modern web apps, and uses a built-in Readability algorithm to extract main content while removing ads, navigation, and other non-essential elements. It supports HTML and Markdown output, and the fetch_urls tool fetches multiple URLs in parallel. Unnecessary resources such as images, stylesheets, and fonts are blocked to save bandwidth. Timeouts, conte…

⭐ 1.1kBrowser AutomationTypeScriptRepo ↗Updated 2026-11-05

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "jae-jae-fetcher-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "fetcher-mcp"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/jae-jae/fetcher-mcp

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "jae-jae-fetcher-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "fetcher-mcp"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers