Puppeteer MCP Server
@merajmehrabi
Puppeteer MCP Server について
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
基本情報
設定
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"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Puppeteer MCP Server?
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.
How to use Puppeteer MCP Server?
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.
Key features of Puppeteer MCP Server
- Navigate web pages and take screenshots
- Click elements, fill forms, select options, hover
- Execute JavaScript in the browser console
- Connect to existing Chrome windows with remote debugging
- Smart tab management that preserves existing Chrome instances
- Detailed logging with Winston (daily rotation, 20MB max, 14 day retention)
Use cases of Puppeteer MCP Server
- Automated web scraping and data extraction
- UI testing and capturing screenshots for verification
- Form filling and submission automation
- Monitoring and interacting with dynamic web pages
FAQ from Puppeteer MCP Server
Can Puppeteer MCP Server connect to an already open Chrome window?
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.
What tools does Puppeteer MCP Server provide?
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.
How do I configure the server with Claude Desktop?
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.
What security precautions are recommended when using remote debugging?
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.
Where are logs stored and how are they managed?
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.
「ブラウザ自動化」の他のコンテンツ
Apify Model Context Protocol (MCP) Server
apifyThe Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
Webpage Screenshot MCP Server
ananddtyagiAn MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.
Umut Naci
firecrawlThe API to search, scrape, and interact with the web at scale. 🔥
mcp-browser-use: MCP server for browser-use
vinayak-mehtaMCP server for browser-use
Fastcrw
usFast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.
コメント