Ghost — Claude Code MCP server for desktop control on Windows
An MCP server that lets an agent drive windows, apps without an API and your browser on Windows and Linux, without hijacking your mouse or screen.
Open on GitHubWhat Ghost does
Ghost sits between the model and the operating system's own control surface. On Windows it uses UI Automation, on Linux AT-SPI2 over D-Bus, so elements come back with their real names, roles and bounds instead of pixel guesses. Work happens in the background: the agent clicks and types inside an app while you keep using another window.
After acting, the server checks again — reading the control's value back or looking at the screen — and reports whether the step was confirmed. Tools cover windows and processes, a terminal, tabs in the browser you are already signed into, the clipboard and waiting for a condition. Anything the agent launches is born on a hidden desktop with its own input queue. No tool call can lift the focus policy; only a person can, by setting GHOST_FOCUS_LOCK=off in the server's environment.
You do not need a vision API key: the driving model reads the element list from ghost_see or the screenshot itself. Ghost targets Windows and Linux, and the Linux path is documented in the project's setup guide. To check the claims on your own hardware, run ghost verify — it exercises the live server over stdio and exits with an error if something does not hold.
What it helps with
- automate a program that has no API and no export
- control windows and processes without stealing the user's focus
- run builds and git commands from an agent on Windows
- pull text out of a third-party interface via accessibility or OCR
- confirm a step really happened instead of trusting an empty ok
Example prompts for the agent
- Walk through the installer in the background and leave my screen alone
- Find the order number field in the open app and type 4417
- Run
git statusin a new terminal window and show me the output
How to install Ghost
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Ghost
How do I install Ghost in Claude Code?
The marketplace entry gives no install command for Claude; the server is wired up by hand following the repository instructions.
What does Ghost do?
It hands an agent the Windows or Linux desktop: clicks, typing, windows, processes, a shell and the browser. Each action gets checked afterwards and comes back with a confirmation.
Do I need a vision API key?
No. The model driving Ghost reads ghost_see or ghost_screenshot itself. Ghost's own vision tier stays off until someone configures it.
