MCP.so
ログイン

Screenshot MCP Server

@codingthefuturewithai

Screenshot MCP Server について

MCP server that provides screenshot capabilities for AI tools, allowing them to capture and process screen content

基本情報

カテゴリ

ブラウザ自動化

ランタイム

python

トランスポート

stdio

公開者

codingthefuturewithai

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": {
    "screenshot_mcp_server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-e",
        "."
      ]
    }
  }
}

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 Screenshot MCP Server?

An MCP server that provides screenshot capabilities for AI tools, allowing them to capture and process screen content. It enables AI assistants to take screenshots of the user's screen and analyze what the user is looking at.

How to use Screenshot MCP Server?

Install from source using uv pip install -e . or pip install -e .. Run in stdio mode with the command-line client screenshot_mcp_server-client output.jpg or start the server via screenshot_mcp_server-server. For SSE mode, run screenshot_mcp_server-server-sse --port 3001. Programmatically, use an MCP client to call the take_screenshot tool.

Key features of Screenshot MCP Server

  • Take full screen screenshots
  • Automatic JPEG compression for efficient transfer
  • Base64 encoded image data for reliable transmission
  • Support for both stdio and SSE transport modes
  • Configurable image quality and optimization
  • Simple command-line interface for testing

Use cases of Screenshot MCP Server

  • AI assistants analyzing the user’s current screen content
  • Automated screenshot capture for debugging or testing
  • Providing visual context for AI decision-making

FAQ from Screenshot MCP Server

What does the Screenshot MCP Server do?

It enables AI tools to capture the user’s screen and return a JPEG image, allowing AI assistants to see and analyze what is on the screen.

What are the system requirements?

Python 3.10 or later (but not 3.13), with dependencies: mcp >= 1.0.0, pyautogui >= 0.9.54, and Pillow >= 10.0.0. It runs on Linux, macOS, and Windows.

What transport modes are available?

Stdio (default) and SSE (runs on port 3001 by default). SSE mode is started with screenshot_mcp_server-server-sse --port 3001.

Does the take_screenshot tool require any parameters?

No, it takes no parameters. The tool returns a JPEG image as base64-encoded data.

How is the screenshot data returned?

The image is returned in JPEG format, base64 encoded for reliable transmission over the MCP protocol.

コメント

「ブラウザ自動化」の他のコンテンツ