広告掲載
MCP.so
ログイン

Stealth Browser MCP Server

@newbeb

リポジトリ

基本情報

カテゴリ

ブラウザ自動化

ライセンス

MIT

トランスポート

stdio

作者

newbeb

Stealth Browser MCP Server について

A MCP Server that provides browser access through playwright with "stealth mode" enabled.

#stealth-browser#browser-automation#mcp-server

Stealth Browser MCP Server の設定

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": {
    "stealth-browser-mcp": {
      "command": "bun",
      "args": [
        "start"
      ]
    }
  }
}

Stealth Browser MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

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 Stealth Browser MCP Server?

An MCP server that provides stealth browser capabilities using Playwright with anti-detection techniques. It allows MCP clients to navigate to websites and take screenshots while evading common bot detection systems.

How to use Stealth Browser MCP Server?

Install dependencies with bun install, then run the MCP server with bun start or use bun dev for development mode. The server exposes a screenshot tool that can be invoked by MCP clients. Use bun inspect to see available tools.

Key features of Stealth Browser MCP Server

  • Stealth mode that bypasses bot detection by modifying browser fingerprints.
  • Full-page or element-specific screenshot capability.
  • Support for both headless and visible browser modes.
  • Uses puppeteer-extra-plugin-stealth with playwright-extra.
  • Built with FastMCP for MCP protocol integration.
  • Built with Bun, a fast JavaScript runtime.

Use cases of Stealth Browser MCP Server

  • Automated website monitoring that evades bot detection.
  • Taking screenshots of webpages without triggering anti-bot measures.
  • Integration with AI agents that need to browse the web stealthily.
  • Collecting visual data from sites that block headless browsers.

よくある質問

1

What does the screenshot tool do?

It takes screenshots of webpages using a stealth browser, with options to capture a full page, a specific CSS element, and run headlessly or visibly.

2

How do I run the server?

Install dependencies with `bun install`, then start the server with `bun start`. For development, use `bun dev`.

3

What parameters does the screenshot tool require?

The only required parameter is `url`. Optional parameters include `fullPage` (boolean, default true), `selector` (CSS selector), and `headless` (boolean, default true).

4

What runtime does this server require?

It requires Bun to run, as the project is built with Bun. Dependencies include FastMCP, Playwright, playwright-extra, and puppeteer-extra-plugin-stealth.

コメント

「ブラウザ自動化」の他のコンテンツ

Firecrawl Mcp Server

mendableai

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

6.9K

Playwright MCP Server 🎭

executeautomation

Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌

5.6K
C

Chrome DevTools for agents

ChromeDevTools

Official Chrome DevTools MCP server from Google that lets coding agents control, debug and profile a live Chrome browser.

53.6K

Fetch MCP Server

zcaceres

A flexible HTTP fetching Model Context Protocol server.

797

Nullprint

nullprintai

Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.

広告掲載