An MCP server for Hyprland desktop automation that allows AI assistants to see the screen, control mouse and keyboard, and manage windows using native Wayland tools. It integrates OCR for text-based interaction and supports complex multi-monitor setups with pixel-accurate coordinate mapping.
Enables AI assistants to automate Hyprland desktop environments through screenshots, mouse/keyboard input, window management, workspaces, clipboard, app launching, and OCR.
Enables background agents to control Hyprland windows, input, screenshots, and session actions while racing actuation paths and refusing stale or unverified focus targets.
MCP server for controlling Hyprland Wayland compositor: screen capture, mouse/keyboard injection, and automation via native Hyprland IPC and wlr protocols.
Enables AI agents to control Hyprland desktops via MCP, including pointer/keyboard input, screenshots, launching apps, and natural-language window targeting using a local decision model.
Provides agents with temporary visual capture of Hyprland/Wayland monitors, windows, or regions as PNGs, enabling visual verification and self-correction of UI and desktop tasks.
Enables MCP clients to inspect and control an Omarchy/Hyprland desktop by taking screenshots, focusing windows, moving/clicking the mouse, scrolling, typing text, and sending keyboard shortcuts.
Enables semantic search over Omarchy, Arch Linux, and Hyprland documentation, allowing users to query configuration and usage information via natural language in Cursor, OpenCode, or Claude Code.
Enables AI agents to control Linux desktops and compositors, including Hyprland/Wayland window management, PipeWire audio routing, systemd diagnostics and self-healing, notifications, screenshots, and optional agent memory.
Gives each agent its own isolated nested Hyprland desktop with a private seat, clipboard and accessibility bus, so it can see the screen and drive a mouse, keyboard, touchpad gestures, windows and apps without touching the user's pointer, focus or windows. Exposes screenshots, zoom, OCR, accessibility-tree control, window management and batched actions as MCP tools, and can optionally act read-only, or with input, on the real desktop.
Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gating.
Enables controlling VRoid Studio through desktop GUI automation, letting an MCP client launch the app, capture its window, locate controls via OCR, edit character parameters, and run save/export flows on macOS and Linux/Hyprland.
Enables an AI agent to see and control a Linux desktop via Wayland/Hyprland, providing screenshots, structured desktop state, pointer/keyboard input, semantic window/workspace tools, and a policy engine for safe execution.
Enables an MCP client to see and drive a Hyprland/Wayland desktop by taking cropped, downscaled screenshots, reading the compositor's window tree, and sending absolute pointer and keyboard input mapped back to global layout pixels. It also exposes off-screen tmux sessions, background task runners, and DevTools-driven Chrome tabs for work that needs no window focus.
An MCP server that enables AI agents to observe and control a Hyprland Wayland desktop using screenshots, accessibility trees, native virtual pointer/keyboard input, and window management. It allows clicking, typing, scrolling, launching apps, and waiting for UI state without uinput, root, or portals, with an optional isolated nested desktop.