広告掲載
MCP.so
ログイン

Web Browser MCP Server

@blazickjp

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

blazickjp

Web Browser MCP Server について

A Minimum Control Program (MCP) server implementation for web browsing capabilities using BeautifulSoup4

Web 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": {
    "web-browser-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "web-browser-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

Web 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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Web Browser Mcp Server?

Web Browser Mcp Server enables AI assistants to browse websites, extract content, and understand web pages through the Model Context Protocol (MCP). It provides smart content extraction using CSS selectors and robust error handling, built with Python 3.11+ and async processing.

How to use Web Browser Mcp Server?

Install via Smithery using npx -y @smithery/cli install web-browser-mcp-server --client claude or manually with uv tool install web-browser-mcp-server. Add the server configuration to your MCP client config file, set the REQUEST_TIMEOUT environment variable (default 30 seconds), and use the browse_webpage tool with a URL and optional CSS selectors.

Features of Web Browser Mcp Server

  • Smart content extraction using CSS selectors
  • Lightning-fast async processing
  • Rich metadata: titles, links, and structured content
  • Robust error handling and timeout management
  • Cross-platform support wherever Python runs

Use cases of Web Browser Mcp Server

  • Browsing and extracting full content from any web page
  • Targeting specific page sections with CSS selectors (headlines, articles, navigation)
  • Providing AI assistants with structured web content for analysis
  • Fetching web data for automated research or summarization workflows

よくある質問

1

What does the browse_webpage tool do?

It fetches a web page and extracts its content, optionally filtering to specific elements defined by CSS selectors you provide.

2

What dependencies or runtime are required?

Python 3.11 or later and the `uv` package manager are required for installation and execution.

3

How is the server configured?

Set the `REQUEST_TIMEOUT` environment variable (default 30 seconds) to control how long the server waits for a webpage response.

4

What transport or authentication does the server use?

The server communicates via the MCP protocol using stdio transport, configured in the MCP client’s JSON configuration. No authentication mechanism is mentioned.

5

What license is Web Browser Mcp Server released under?

It is released under the MIT License.

コメント

「ブラウザ自動化」の他のコンテンツ

browser-use-mcp-server

co-browser

Browse the web, directly from Cursor etc.

827

Scrapling Fetch MCP

cyberchitta

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

101

QuantumProxies — Residential, Mobile & Datacenter Proxy MCP Server

quantumproxies

Give your AI agent its own proxies. QuantumProxies exposes residential, mobile, datacenter, ISP and IPv6 endpoints as MCP tools: list your plans, generate ready-to-use proxy strings with credentials, target by country, s

playwright-server MCP server

blackwhite084

189

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
広告掲載