@merajmehrabi
基本情報
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"puppeteer-mcp-server": {
"command": "npx",
"args": [
"puppeteer-mcp-server"
]
}
}
}Connect to an existing Chrome instance with remote debugging enabled
Navigate to a URL
Take a screenshot of the current page or a specific element
Click an element on the page
Fill out an input field
Select an element on the page with Select tag
Hover an element on the page
Execute JavaScript in the browser console
Puppeteer MCP Server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows. It is designed for developers using AI assistants like Claude to automate web tasks.
Install globally via npm (npm install -g puppeteer-mcp-server) or run directly with npx puppeteer-mcp-server. Configure it as an MCP server in Claude Desktop or Claude VSCode Extension settings. Use tools such as puppeteer_navigate, puppeteer_screenshot, puppeteer_click, puppeteer_fill, puppeteer_select, puppeteer_hover, puppeteer_evaluate, and puppeteer_connect_active_tab to control the browser.
Yes, use Active Tab Mode: launch Chrome with `--remote-debugging-port=9222`, then call the `puppeteer_connect_active_tab` tool to connect to a specific tab or the default non-extension tab.
It includes `puppeteer_navigate`, `puppeteer_screenshot`, `puppeteer_click`, `puppeteer_fill`, `puppeteer_select`, `puppeteer_hover`, `puppeteer_evaluate`, and `puppeteer_connect_active_tab`. Each tool has required and optional parameters documented in the README.
Add a `"puppeteer"` entry under `"mcpServers"` in your `claude_desktop_config.json`. The command depends on installation method: use `"puppeteer-mcp-server"`, `"npx"` with args `["-y", "puppeteer-mcp-server"]`, or `"node"` with the path to the built index file.
Only enable remote debugging on trusted networks, use a unique debugging port, close it when not in use, and never expose the port to public networks.
Logs are stored in a `logs/` directory with daily rotation, maximum file size of 20MB, retention of 14 days, and automatic compression of old logs. Logging levels include DEBUG, INFO, WARN, and ERROR.
A flexible HTTP fetching Model Context Protocol server.
Parse allows your agent to access thousands of APIs instantly. You can use Parse to build an API for any action on any website and edit any previously existing API in our catalogue.
Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.
Playwright MCP server
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
コメント