playwright-fetch

The Playwright Fetch MCP Server is designed to enable language models to retrieve and process JavaScript-rendered content from web pages. By leveraging Playwright, a powerful browser automation tool, this server can render web pages with full JavaScript support, extract the main content, and convert it into markdown format for easier consumption by language models. It supports pagination for handling large content, respects robots.txt directives, and can route requests through a proxy server. The server is available as a pre-built Docker image, making it easy to deploy and integrate into various environments.

Features

• Browser Automation: Uses Playwright to render web pages with full JavaScript support.
• Content Extraction: Automatically identifies and extracts main content areas from web pages.
• Markdown Conversion: Converts HTML to clean, readable markdown.
• Pagination Support: Handles large content through pagination.
• Robots.txt Compliance: Respects robots.txt directives for autonomous fetching.

MCP Tools

• playwright-fetch: Fetches a URL using Playwright browser automation and extracts its contents as markdown.

Usage with Different Platforms

Configure for Claude.app using uvx

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

Configure for Claude.app using docker

"mcpServers": {
  "playwright-fetch": {
    "command": "docker",
    "args": ["run", "-i", "--rm", "threatflux/playwright-fetch"]
  }
}

Configure for VS Code using uvx

{
  "mcp": {
    "servers": {
      "playwright-fetch": {
        "command": "uvx",
        "args": ["mcp-server-playwright-fetch"]
      }
    }
  }
}

Configure for VS Code using Docker

{
  "mcp": {
    "servers": {
      "playwright-fetch": {
        "command": "docker",
        "args": ["run", "-i", "--rm", "threatflux/playwright-fetch"]
      }
    }
  }
}