mcp-playwright-scraper

A Model Context Protocol (MCP) server that scrapes web content and converts it to Markdown.

Overview

This MCP server provides a simple tool for scraping web content and converting it to Markdown format. It uses:

• Playwright: For headless browser automation to handle modern web pages including JavaScript-heavy sites

• BeautifulSoup: For HTML parsing and cleanup

• Pypandoc: For high-quality HTML to Markdown conversion

Tools

The server implements a single tool:

• scrape_to_markdown: Scrapes content from a URL and converts it to Markdown

  • Required parameter: url (string) - The URL to scrape

  • Optional parameter: verify_ssl (boolean) - Whether to verify SSL certificates (default: true)

Installation

Using uv (recommended)

When using uv no specific installation is needed. We will use uvx to directly run mcp-playwright-scraper.

Using PIP

Alternatively you can install mcp-playwright-scraper via pip:

After installation, you can run it as a script using:

Prerequisites

• Python 3.11 or higher

• Playwright browser dependencies

• Pandoc (optional, will be automatically installed by pypandoc if possible)

After installation, you need to install Playwright browser dependencies:

Configuration

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

Usage with Claude Code

Usage with Zed

Add to your Zed settings.json:

Usage with Cursor

1. Open Cursor Settings

   • Navigate to Cursor Settings > Features > MCP

   • Click the "+ Add New MCP Server" button

2. Configure the Server

   • Name: mcp-playwright-scraper

   • Type: Select stdio

   • Command: Enter one of the following:

Usage

Once configured in Claude Desktop, you can explicitly use the scraper with a prompt like:

Debugging

You can use the MCP inspector to debug the server:

Or if you've installed the package in a specific directory or are developing on it:

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Development

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

2. Build package distributions:

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

Note: You'll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN

• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

License

This MCP server is licensed under the Apache License, Version 2.0. You are free to use, modify, and distribute the software, subject to the terms and conditions of the Apache License 2.0. For more details, please see the LICENSE file in the project repository or visit http://www.apache.org/licenses/LICENSE-2.0.