Best Wayland MCP Servers
Wayland is a protocol for a compositor to talk to its clients as well as a C library implementation of that protocol. The compositor can be a standalone display server running on Linux kernel modesetting and evdev input devices, an X application, or a wayland client itself.
Why this server?
Allows running and interacting with graphical programs in sealed Wayland sessions, including starting a headless Wayland compositor and using accessibility trees, screenshots, and input simulation.
AlicenseAqualityAmaintenanceRuns real GUI programs in a sealed X11 or Wayland session where an agent can read the accessible tree, take screenshots and clips with sound, click, type and drive gamepads. Then it checks what it finds: unnamed controls, contrast, Tab order, screen reader announcements and audio dropouts.618225 npm232 PyPI1MITWhy this server?
Collects focus and idle events from the Wayland compositor to track active windows and user activity.

roxabi-senseofficial
AlicenseBqualityBmaintenanceLocal workstation attention journal that tracks focus, idle, and agent sessions, exposing timeline data via MCP for AI agents to query current or past activity.5AGPL 3.0Why this server?
Provides tools for detecting the Wayland display protocol and desktop environment identifiers, as well as runtime configuration details for the desktop session.
Why this server?
Provides explicit support for Wayland display server with automatic detection and configuration of necessary environment variables
AlicenseAqualityCmaintenanceEnables browser automation for LLMs on Linux display servers, supporting web interaction, screenshots, and JavaScript execution in a real browser.74 npm7MITWhy this server?
Enables AI-driven desktop automation for Wayland-based systems, including visual analysis through screenshots, absolute/relative mouse control, and keyboard input simulation.
AlicenseAqualityAmaintenanceEnables AI assistants to automate Wayland desktop environments through screenshot analysis, mouse control, and keyboard input simulation. It supports visual context via VLM providers like Gemini and OpenRouter to perform complex, multi-step desktop actions.1036 PyPI15GPL 3.0Why this server?
Enables input injection and screen capture within Wayland-based GNOME sessions, bypassing protocol-level security restrictions through a dedicated shell extension.
AlicenseBqualityCmaintenanceGNOME desktop automation for AI agents. 30 tools via D-Bus: screenshots, window management, mouse/keyboard injection, clipboard, workspaces, and system notifications. Works on any GNOME 45–49 Linux desktop.3015GPL 3.0Why this server?
Uses Wayland protocols for virtual input and screenshots, enabling native interaction with the Wayland desktop.
AlicenseAqualityAmaintenanceAn MCP server for Hyprland that enables AI agents to control workspaces, windows, mouse, keyboard, and take screenshots on a Wayland desktop.14269 PyPI39MITWhy this server?
Backend for driving apps on Wayland compositors, providing headless display isolation, input, accessibility, and logs.
AlicenseAqualityAmaintenanceBuild -> See -> Interact -> Debug over native GUI apps.3120Apache 2.0Why this server?
Offers screen capture capabilities on Wayland compositors using grim (wlroots screencopy protocol), supporting region, window, and fullscreen screenshots.
AlicenseAqualityCmaintenanceGives AI agents eyes on Hyprland Wayland desktops by capturing screenshots via grim and offering optional image analysis with Gemini API.6MIT