computer-control-mcp

Source Code

Description

computer-control-mcp is an MCP server that enables desktop automation, including mouse control, keyboard input, screenshots, OCR, and window management. It allows large language models (LLMs) or other agents to interact with graphical user interfaces. The server is implemented using PyAutoGUI, RapidOCR, and ONNXRuntime, and is designed to have zero external dependencies. It is similar in functionality to 'computer-use' by Anthropic.

Features

• Mouse control (move, click, etc.)
• Keyboard control (type, press keys, etc.)
• Screen management (taking screenshots)
• Window management
• Optical Character Recognition (OCR) using RapidOCR and ONNXRuntime
• Zero external dependencies (all required packages are included)
• API for programmatic interaction

Category

code-execution-automation-mcp-servers

Tags

mcp, automation, desktop, gui

Pricing

No pricing information provided. The project is open source and released under the MIT License.