What operating system does UI Explorer MCP Server support?
Windows.
@modularflow
基本情報
MCP Server for tools to explore the UI on your computer.
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": {
"mcp-ui-explorer": {
"command": "python",
"args": [
"record_macro.py",
"--name",
"Login Workflow"
]
}
}
}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。
UI Explorer MCP Server is an MCP server that provides tools for exploring and interacting with UI elements on your screen. It is designed for developers and testers who need to automate UI workflows on Windows.
Install the package via pip install mcp-ui-explorer or clone the repository. Then, configure your MCP client (e.g., Roo in Cursor or Claude Desktop) with the server command uvx mcp-ui-explorer. Use the provided MCP tools like explore_ui, screenshot_ui, and click_ui_element to scan and control UI elements.
Windows.
Use `pip install mcp-ui-explorer` or clone the repository and install in development mode with `pip install -e .` or `uv pip install -e .`.
Run `python record_macro.py --name "My Workflow"` to record and `python play_macro.py --file "macros/My Workflow.json"` to playback. Windows users can use the provided batch files.
`explore_ui`, `screenshot_ui`, `click_ui_element`, and `keyboard_input`.
Python 3.10+, MCP 1.6.0+, PyAutoGUI, PyWinAuto, Pillow, and Pydantic 2.0+.
A search tool helps dev to solve the naming things problem.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Open-source MCP to use Blender with any LLM
コメント