Computer Control MCP

Name: Computer Control MCP
Author: AB498

@AB498

Computer Control MCP について

MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies.

#automation #mcp #computer-use

基本情報

カテゴリ

生産性

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

AB498

投稿者

AB498

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": {
    "computer-control-mcp": {
      "command": "uvx",
      "args": [
        "computer-control-mcp@latest"
      ]
    }
  }
}

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 Computer Control MCP?

An MCP server that provides computer control capabilities like mouse, keyboard, and OCR via PyAutoGUI, RapidOCR, and ONNXRuntime. It is similar to Anthropic’s “computer-use” and advertises zero external dependencies.

How to use Computer Control MCP?

Install with uvx computer-control-mcp@latest (first run downloads ~70 MB of Python dependencies) or via pip install computer-control-mcp. Configure the server in your MCP client’s settings under mcpServers and then invoke its tools through the client.

Key features of Computer Control MCP

Control mouse movements and clicks
Type text at the current cursor position
Take screenshots with optional GPU‑accelerated capture (Windows only)
Extract text from screenshots using OCR
List and activate open windows
Press keyboard keys and key combinations
Drag and drop operations
Configurable screenshot save directory and automatic WGC patterns

Use cases of Computer Control

「生産性」の他のコンテンツ

TickTick MCP Server

alexarevalo9

A Model Context Protocol (MCP) server designed to integrate with the TickTick task management platform, enabling intelligent context-aware task operations and automation.

MCP Shrimp Task Manager

cjo4m06

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning A

2.1K