$ loading_
Control remote desktops via VNC with OCR-assisted screen reading.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Claude KVM" MCP server from askskill: Run: claude mcp add 'io-github-aras-workspace-claude-kvm' -- npx -y claude-kvm
Use Claude KVM to connect to the remote desktop, then open the specified app, click through menus, and enter text to complete the task.
Mouse and keyboard actions performed on the remote desktop.
Use Claude KVM to inspect the current remote desktop and identify on-screen buttons, prompts, or error messages.
Readable UI text and key information extracted.
When an ops or engineering user needs to inspect and operate a remote desktop, it can interact via VNC. OCR also helps identify text on the screen.
When a task cannot be completed from the command line and requires GUI interaction, this tool can execute remote desktop actions.
It is an MCP server for controlling remote desktops via VNC. The description also mentions a native Swift daemon and Apple Vision OCR.
It can let an AI perform mouse and keyboard actions on remote desktops and help recognize on-screen text. Exact capabilities depend on the implementation.
The provided info only says it controls remote desktops via VNC and uses a native Swift daemon and Apple Vision OCR. For exact setup or dependencies, see the source repository.
Enable AI agents to remotely control a dedicated macOS session for automation.
Enable MCP-compatible models to control desktop apps over VNC remotely.
Let AI control macOS apps, mouse, and keyboard to automate tasks.
Remotely control Claude Code instances to run commands and manage files.
Let AI agents discover macOS windows and capture screenshots for UI debugging.
Capture thoughts, connect ideas, and track thinking changes through natural conversation.