MCP.so
ログイン

puppeteer-mcp-server

@AnyContext-ai

リポジトリ

puppeteer-mcp-server について

概要はまだありません

#puppeteer#browser-automation#llm-integration

基本情報

カテゴリ

ブラウザ自動化

ランタイム

node

トランスポート

stdio

公開者

AnyContext-ai

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": {
      "type": "http",
      "url": "http://localhost:8000"
    }
  }
}

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 is a Model Context Protocol (MCP) server that provides browser automation capabilities using Puppeteer. It enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

How to use puppeteer-mcp-server?

Build the Docker image with docker build -t puppeteer-mcp-server . and run it with docker run --rm -p 8000:8000 puppeteer-mcp-server. The server then exposes browser automation tools via the MCP protocol on port 8000.

Key features of puppeteer-mcp-server

  • Browser automation via Puppeteer
  • Web page interaction and navigation
  • Screenshot capture of web pages
  • JavaScript execution in a real browser
  • Exposed as an MCP server for LLMs

Use cases of puppeteer-mcp-server

  • LLM-driven web browsing and data extraction
  • Automated visual regression testing with screenshots
  • Dynamic JavaScript execution for scraping single-page applications
  • Interactive web page exploration for AI agents

FAQ from puppeteer-mcp-server

What does puppeteer-mcp-server do?

It provides browser automation using Puppeteer, allowing LLMs to interact with web pages, capture screenshots, and execute JavaScript through the Model Context Protocol.

What are the runtime requirements?

The server is packaged as a Docker container and requires a compatible Docker runtime. Puppeteer and its bundled Chromium are included in the Docker build.

How do I build and run puppeteer-mcp-server?

Build with docker build -t puppeteer-mcp-server . and run using docker run --rm -p 8000:8000 puppeteer-mcp-server.

コメント

「ブラウザ自動化」の他のコンテンツ

BrowserTools MCP

AgentDeskAI

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

7.3K

Umut Naci

firecrawl

The API to search, scrape, and interact with the web at scale. 🔥

148.0K

Puppeteer Vision Mcp Server

djannot

48

Fetch MCP Server

zcaceres

A flexible HTTP fetching Model Context Protocol server.

797

Fastcrw

us

Fast, 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.

286