Control Remote macOS Desktops with AI
Open-source MCP server that enables AI to control remote macOS systems via screen sharing, providing screenshot capture, keyboard input, mouse control, and
Why it matters
Enable AI to fully control remote macOS systems via screen sharing, offering a direct alternative to OpenAI Operator with complete desktop capabilities.
Outcomes
What it gets done
Capture screenshots of remote macOS desktops.
Send keyboard and mouse inputs to remote macOS machines.
Open applications and interact with the macOS GUI.
Automate tasks like social media engagement and content creation.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-computer-use-remote-macos-use | bash Capabilities
Tools your agent gets
Captures a screenshot of the remote macOS desktop
Sends keyboard input to a remote macOS machine
Moves the mouse cursor to specified coordinates on a remote macOS machine
Performs a mouse click at specified coordinates on a remote macOS machine
Performs a double-click at specified coordinates on a remote macOS machine
Performs mouse scrolling at specified coordinates on a remote macOS machine
Opens/activates an application and returns its PID for further interactions
Performs a mouse drag-and-drop operation from start to end point on remote macOS
Overview
Computer-Use - Remote macOS Use MCP Server
What it does
This MCP server provides remote control capabilities for macOS systems through screen sharing. It offers eight tools for desktop interaction: screenshot capture, keyboard input, mouse movement, clicking, double-clicking, scrolling, drag-and-drop operations, and application launching. The server connects to remote Macs using Apple Authentication protocol and requires only Screen Sharing to be enabled on the target machine-no additional software installation needed. It runs via Docker and supports WebRTC through LiveKit for real-time screen sharing.
How it connects
Use this server when you need to control a remote macOS machine programmatically through an MCP client. It's designed for scenarios where you want AI to interact with macOS applications and desktop interfaces remotely, such as the documented examples of Twitter operations, CapCut usage, Mail App workflows, and LinkedIn/Twitter interactions. The tool is particularly useful when you want to avoid installing background agents on the target Mac and prefer a screen-sharing-based approach that works across all macOS versions.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.