$ loading_
Capture Linux screenshots and control mouse and keyboard via MCP, including Wayland.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "desktop-mcp" yet — see the docs or source repo.
Please help me open an app on my Linux desktop, click buttons, and complete a repetitive task; take screenshots first if needed to confirm the current screen.
Produces screen-based desktop actions and executes mouse/keyboard control.
Please check whether buttons in a Linux desktop UI are clickable and report the current state based on screenshots.
Returns screenshot-based checks and helps with simple manual-style UI verification.
Based on the current desktop screenshot, tell me where to click next and perform the mouse and keyboard actions for me.
Provides screen-aware guidance and performs the corresponding input.
Useful when you want AI to operate a Linux GUI directly, such as repetitive clicks, form filling, or app switching. It can inspect the screen via screenshots and then perform mouse and keyboard actions.
Useful for developers or testers validating interfaces in Linux, including Wayland. It can help confirm the UI is rendered correctly and perform basic interaction checks.
Useful when you need screen-aware assistance, such as remote help or unclear instructions. The tool can inspect screenshots first, then click and type on your behalf.
It is an MCP tool that lets LLMs take desktop screenshots and control the mouse and keyboard on Linux. The description explicitly mentions Wayland support.
According to the description, it targets Linux desktop environments, including Wayland. Other prerequisites are not specified in the provided information.
It uses MCP to let an LLM understand the interface from screenshots and then perform mouse and keyboard actions. See the source repository for implementation details.
Let AI see and control a Linux desktop for visual task automation.
Control a Linux desktop for screenshots, input, window actions, and clipboard tasks.
Let AI inspect and control Windows desktops and apps semantically.
Capture Windows desktop screenshots so AI can inspect interfaces for development and debugging.
Capture desktop or window screenshots with clipboard support across major platforms.
Automate Windows desktop tasks with screenshots, window control, and input actions.