hypruse
hypruse gives an AI agent full mouse/keyboard/screen control of a live Hyprland Wayland desktop — semantic window management, screenshots with a zoom loop, accessibility-tree control targeting, and app launching — with no compositor plugin, root, or X11.
See the desktop semantically:
desktopreturns monitors, workspaces, windows (address/class/title/geometry), active window, cursor, and layer surfaces (bars, launchers, notification popups) in one call — no pixels needed.Capture and inspect visually:
screenshot(monitor, window, or region; JPEG/PNG, optional stable-frame wait) andzoom(native-resolution re-capture around a point) return coordinate-mapping metadata for a coarse-to-fine clicking loop.Target controls by name:
uireads an app's AT-SPI accessibility tree with exact global coordinates and current values (text, slider percent, checkbox state);marksdraws numbered marks over a screenshot;click_uipresses a control by name or mark number in one call.Drive input:
pointer(move/click/drag/scroll),keyboard(unicode-safe typing and app-level combos, optionally aimed at a specific window), andsequenceto run an ordered micro-plan in a single round-trip.Manage windows over IPC:
hyprswitches workspaces and focuses/moves/closes/fullscreens/floats windows instantly;launchstarts apps (silently on the agent's own hidden workspaces by default) and blocks on the real window-open event.Use the user's own setup:
bindslists the user's Hyprland keybinds anduse_bindexecutes one by combo (launchers, scratchpads, layout shortcuts).Wait for real events:
wait_forblocks on compositor events (window open/close, workspace switch, title change, layer open/close, urgency, screen sharing) instead of polling.Observe results inline: acting tools accept
then='desktop'|'screenshot'|'ui', fusing a fresh view of the effect into the same call.Work in the background: on windows the human isn't in, actions go through accessibility actions and
sendshortcut, leaving the user's cursor, focus, and workspace untouched.Guard rails: read-only mode plus opt-in confinement, auth-dialog guard, strict seat checks, window marking, journal/dry-run/replay, and optional clipboard access bound what the agent may touch.
Also usable as shell verbs: all fifteen tools are also CLI commands with compact text output and meaningful exit codes, for agents that don't speak MCP.
Extras (env-gated):
clipboardread/write via wl-clipboard whenHYPRUSE_CLIPBOARD=1.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@hypruse Take a screenshot of my focused window."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
hypruse
Your AI agent works in apps on its own Hyprland workspaces while you keep working on yours. hypruse is an MCP server, a set of shell verbs and an agent skill that give an agent the desktop you already have: the window tree, screenshots, clicks on controls by name, a mouse and a keyboard. It runs on stock Hyprland and on Omarchy, with no compositor plugin, no root, no portals, no ydotool daemon and no X11.

Quick start
yay -S hypruse # or: uv tool install hypruse
hypruse init # registers it with Claude Code, Codex or Claude Desktop (asks first), then runs doctorThen ask your agent: "Use hypruse to list the windows on each of my workspaces." It answers from Hyprland's own window tree, without a screenshot. When you want it to work out of your sight, ask it to launch an app on its own workspace and do the job there: that is Background mode.
On Omarchy, everything hypruse needs is already installed; On Omarchy covers the one browser flag to set and a safe default for Omarchy's no-prompt agent launcher. If doctor reports a failure, Troubleshooting has the fix for each line. Before you hand an agent your seat, read the Security model.
Den builds its desktop control on hypruse, and hyprvibe and the NUR package it for NixOS.
Related MCP server: kwin-mcp
Why
Computer use exists on macOS and Windows, and the vendors' Linux apps still ship without it: Claude Desktop's Linux docs say computer use is not available there, and ChatGPT's computer use covers macOS and Windows only. Anthropic's reference implementation is an X11 container. Other Wayland tools lean on ydotool and uinput, on GNOME-only portals, or on a compositor plugin built for one exact Hyprland version.
Meanwhile Hyprland already exposes everything an agent needs, better than any accessibility bridge: a complete IPC surface for state and window management, and first-class Wayland protocols for input. hypruse just wires them to MCP:
Semantic first.
desktopreturns the real window/workspace tree (addresses, classes, titles, geometry) in one call. The agent switches workspaces and focuses windows the way you do (instantly, over IPC), not by squinting at pixels.Vision when it matters. Screenshots of a monitor, one window (with grim 1.5+ on Hyprland 0.54+, captured as itself even on a hidden workspace or under another window, though a hidden app may show how it last looked), or a zoomed region, with the geometry/scale metadata to map any pixel back to a clickable coordinate: a coarse-to-fine loop grounded in the GUI-agents research.
Native input. Clicks and scrolls are spoken directly over the Wayland wire (
zwlr_virtual_pointer_v1); typing goes throughwtype's virtual keyboard with a proper XKB keymap, unicode-safe on any layout.Works beside you. The agent can work in apps on its own workspaces while you keep working on yours. It presses controls through the accessibility tree and types through it or with Hyprland's
sendshortcut, so your cursor, keyboard focus and workspace stay where you left them. Stock Hyprland, no compositor plugin: see Background mode.
Install
Requirements: Hyprland (both config managers: hyprland.conf and the Lua hyprland.lua that 0.56 introduced), grim (grim 1.5+ on Hyprland 0.54+ lets a window screenshot capture the window itself, and hypruse doctor says whether yours can), wtype (most Hyprland setups already have both), and, for the uvx route, uv. The accessibility tools (ui/marks/click_ui) use busctl, which ships with systemd, to find the accessibility bus, then talk to it over one connection of their own. Optional: wl-clipboard for the opt-in clipboard tool, imagemagick for numbered marks captures.
Arch Linux, from the AUR:
yay -S hypruse # or hypruse-git for mainThen let it set itself up and verify the environment:
hypruse init # detects your MCP clients, registers (asks first), offers the agent skill, runs doctor
hypruse doctor # just the diagnosticsManual registration, Claude Code:
claude mcp add -s user hypruse -- uvx hypruseFrom a source checkout:
claude mcp add -s user hypruse -- uv run --directory /path/to/hypruse hypruseAny other MCP client: run uvx hypruse as a stdio server. hypruse is also in
the official MCP registry as
io.github.IlyasKhallouki/hypruse, so clients that browse the registry can
install it from there.
Read-only mode: set HYPRUSE_READONLY=1 in the server config to expose only the observation tools (desktop, screenshot, zoom, ui, marks, binds, wait_for). The agent can see and narrate but cannot click, type, or launch. A good first week.
Claude Code plugin
The plugin holds the MCP server and the agent skill. Add this repository as a plugin marketplace, then install the plugin from it:
claude plugin marketplace add IlyasKhallouki/hypruse
claude plugin install hypruse@hypruseInside a session, /plugin marketplace add IlyasKhallouki/hypruse and /plugin install hypruse@hypruse do the same. The plugin starts its server from its own copy of the source with uv run --locked, so it runs exactly the code the plugin ships, with the dependency versions in the committed uv.lock. It needs uv even when hypruse is installed another way, and the first start takes a few seconds while uv sets up a virtual environment inside the plugin's folder. If you registered hypruse earlier with hypruse init or claude mcp add, run claude mcp remove -s user hypruse first, or Claude Code lists every tool twice. For the same reason, remove the ~/.claude/skills/hypruse link if hypruse skill install made one. After a release, claude plugin update hypruse@hypruse fetches the new version.
The plugin works in Claude Code on a Linux machine running Hyprland. Cowork starts the server only when the session runs on your own computer, and hypruse has not been tested there. Chat on claude.ai (on the web, in the desktop app and on mobile) loads the skill but never starts the server, so the plugin has nothing to drive there. macOS and Windows are not supported.
What the plugin runs and sends: it has no hooks, and its one program is the MCP server above. On first start, uv installs the dependency versions locked in uv.lock from PyPI into a virtual environment in the plugin's folder; hypruse itself runs from the plugin's own source. After that the server talks only to local sockets (Hyprland's IPC, the Wayland display and the accessibility bus), makes no network connections and has no telemetry. It runs the desktop tools listed under Requirements (hyprctl, grim, wtype and busctl, plus ImageMagick for marks and wl-clipboard for the opt-in clipboard tool), and launch runs the command the agent gives it through Hyprland's exec. Screenshots, window titles and control names go only to your own Claude session, as tool results; Security model lists what stays on disk, and PRIVACY.md says the same in short. The skill's allowed-tools let Claude run the read-only shell verbs (hypruse doctor, desktop, screenshot, zoom, ui, marks, binds, wait_for and --help) and its Read tool, which opens the screenshot files, without a prompt. The shell verbs need hypruse on PATH; the plugin's MCP tools and every verb that clicks, types or launches still ask unless you allow them.
Things to ask once it is installed:
"Use hypruse to list the windows on each of my workspaces."
"Take a screenshot of my screen and tell me which apps are open."
"Switch to the workspace where btop is running and tell me which process is using the most CPU."
Nix
The repository is a flake for x86_64-linux and aarch64-linux. To try it without installing anything:
nix run github:IlyasKhallouki/hypruse -- doctorInstall it before you run hypruse init. init registers the hypruse it finds on PATH, and a nix run copy is not on it, so init would fall back to uvx. For a quick install, run nix profile add github:IlyasKhallouki/hypruse (older Nix calls it nix profile install). In a flake:
{
inputs.hypruse = {
url = "github:IlyasKhallouki/hypruse";
inputs.nixpkgs.follows = "nixpkgs";
};
}Then add inputs.hypruse.packages.${pkgs.stdenv.hostPlatform.system}.default to environment.systemPackages or home.packages, or add inputs.hypruse.overlays.default to nixpkgs.overlays and use pkgs.hypruse.
With Home Manager, import the module instead:
{
imports = [ inputs.hypruse.homeModules.default ];
programs.hypruse.enable = true;
programs.hypruse.env.HYPRUSE_BACKGROUND = "1"; # optional, the server's environment
programs.mcp.enable = true;
programs.claude-code.enableMcpIntegration = true; # if Home Manager manages Claude Code
}The module installs hypruse and adds it to programs.mcp.servers, the shared list of MCP servers that Home Manager's Claude Code module and other client modules read. On a Home Manager release without programs.mcp, the module only installs the package. If Home Manager does not manage your client, register the installed binary by hand: claude mcp add -s user hypruse -- "$(command -v hypruse)".
The package wrapper appends grim, wtype, wl-clipboard, ImageMagick and systemd's busctl to the end of PATH, so the copies your session already has take precedence. It leaves out hyprctl, which has to match the running compositor, so hypruse uses the one your Hyprland session provides. If a client starts hypruse without that PATH, hypruse.override { withHyprctl = true; } appends nixpkgs' hyprctl as a last resort.
On Omarchy
grim, wtype, ImageMagick and wl-clipboard ship with Omarchy, and mise installs
uvthe first time you run it, soyay -S hypruseandhypruse initare all it takes.initregisters the installedhypruserather thanuvx, because an MCP client started outside your shell may not find mise'suvxshim.Chromium, Omarchy's web apps and Obsidian build an accessibility tree only when asked. Without one,
click_ui,uiand background mode fall back to screenshots in them. Add--force-renderer-accessibilityon its own line to~/.config/chromium-flags.conf(Chromium and its web apps) and to~/.config/obsidian/user-flags.conf(Obsidian), then restart the app.hypruse doctornames any open window that still has no tree.Omarchy's agent launcher (
Super + Shift + Ctrl + A, oromarchy agent prompt) starts agents in their no-approval modes, which removes the approval prompt the Security model leans on. Start withHYPRUSE_BACKGROUND=1, which keeps hypruse's input on the agent's own workspaces, orHYPRUSE_READONLY=1, which lets it only look:claude mcp add -s user -e HYPRUSE_BACKGROUND=1 hypruse -- "$(command -v hypruse)"Omarchy 4 has no Waybar, so the Waybar indicator does not apply. Bind the emergency stop to a free key in your Hyprland config instead, for example
bind = SUPER SHIFT, BackSpace, exec, hypruse stop.Omarchy keeps a separate Claude Code setup per agent account, and a server added with
claude mcp addreaches only the account it was added in. Runhypruse initagain in each account you use.
Troubleshooting
hypruse doctor checks each part on its own. What to do about each line it can print:
doctor says | what to do |
| Install what it names, for example |
| Run hypruse inside your Hyprland session. A client in a VM, a container or another user's session cannot reach your compositor. |
| The process found Hyprland but cannot reach its sockets or its Wayland display, which again means it is not running inside your session. |
| Run |
| Install |
| That app has no accessibility tree yet. Add |
| Window screenshots crop the screen until you have grim 1.5+ on Hyprland 0.54+. Everything else works. |
Problems doctor cannot see:
If the MCP server exits as soon as it starts on Arch, CachyOS or Omarchy, you are on hypruse 0.13.0 or older, which does not start with
python-mcp2. Arch has shipped mcp 2 since 2026-10-27. Upgrade to 0.13.1 or later.If the client says
uvx: command not found, it does not see your shell'sPATH. Register the installed binary instead:claude mcp add -s user hypruse -- "$(command -v hypruse)", or runhypruse initagain.If Claude Desktop shows no screenshots, set
HYPRUSE_SCREENSHOT_MODE=imagein its config, as below.
Claude Desktop (Linux beta)
The Linux beta ships without Anthropic's first-party computer use, but stdio MCP servers work in chat, which makes hypruse the workaround. In ~/.config/Claude/claude_desktop_config.json:
{
"mcpServers": {
"hypruse": {
"command": "uvx",
"args": ["hypruse"],
"env": { "HYPRUSE_SCREENSHOT_MODE": "image" }
}
}
}Two Desktop-specific notes: use image mode (Desktop renders inline MCP images and has no file-read tool), and the app must run natively inside your Hyprland session so the server inherits WAYLAND_DISPLAY/HYPRLAND_INSTANCE_SIGNATURE; from a VM or container it cannot reach your compositor. If your Desktop install bypasses tool-approval prompts, treat the Waybar indicator + panic keybind as mandatory, not optional.
Background mode
An agent can work in apps on workspaces you are not looking at while you keep working on your own. On stock Hyprland, with no compositor plugin, hypruse does not move your cursor, take your keyboard focus or switch your workspace to do it. An app can still bring one of its own windows forward in response to something the agent did; when that changes your focused window, the result says so.
It is on by default, in automatic mode. An action on the window you are in runs on your screen, as it always has. An action on any other window runs in the background:
click_uipresses the control through its accessibility action. A text field gets the app's own focus instead (except in GTK 4, which does not allow it). When no button, box or field matches the name,click_uialso takes a named element of another role that has an action, such as a row in a web app's list. Some of those actions only focus the element (Qt WebEngine's rows offer nothing else). The result then says it focused the element and whether the app reports it focused. That does not open the row: in testing, Enter sent to a focused Qt WebEngine row did not open it either.keyboardwithwindow=types into the window's focused text field (or its only one) through the accessibility interface. Otherwise it sends the keys to that window alone with Hyprland'ssendshortcut, one key at a time on your keyboard layout. Newlines, tabs and backspaces are always sent as keys. Keys go to the control the app itself has focused, which is not necessarily the field text went into, so the agent focuses a field withclick_uibefore sending keys to it.launchwith no workspace opens the app on one of the agent's own workspaces, out of your sight.The pointer is your real cursor, so it cannot work in the background. It is refused where its input would land on a window other than yours, and the refusal points the agent at
click_ui.
What the background cannot do is refused with the reason and what to do instead. background=false on a call (--foreground on the CLI) does it on your screen.
Settings
The guarantee overrides everything. Without it, a call's own background argument wins over the automatic rule.
setting | what it does |
| The guarantee. The agent works only on windows on its own workspaces. The pointer, workspace switches, |
| Per call, on |
unset | Automatic, as above. |
| Off: actions run on your screen as in 0.12, unless a call passes |
The guarantee bounds hypruse's own input. It cannot bound what a program does once launch starts it: the command runs as given, through a shell, so keep launch behind your client's approval prompt even with HYPRUSE_BACKGROUND=1.
The agent's workspaces are HYPRUSE_AGENT_WORKSPACES, 99 down to 90 by default, at the far end of the numbers so they stay clear of the ones you use. A-B counts in either direction, and a comma list (99,98,50) or named workspaces (name:research) work too. HYPRUSE_AGENT_FILL (default 1) is how many of the agent's apps share one workspace before the next one is used. With 1, every app gets a workspace to itself, which keeps hidden windows at their full size. A workspace in the range that holds one of your windows is skipped, so yours and the agent's never mix, and so is one you are looking at. When the whole range is full the next app goes where the agent has the fewest. A window an earlier session opened counts as the agent's when HYPRUSE_MARK tagged it. With HYPRUSE_CONFINE=workspace:..., apps open only on agent workspaces inside that scope, and on yours as before when there is none.
launch waits for its own window: one that opens on the workspace it asked for, or one of the launched program's own class. A window of another app that you open meanwhile is left alone; one of the same app can be taken for the launched one. An app that is already running (a browser, often) opens its new window from the running process, which ignores the workspace rule, so it appears on your screen and takes your focus until hypruse moves it; the result says so, and under the guarantee it carries a warning. Start a separate instance for the agent (for a browser, a separate profile) to avoid it.
What you get back
Every background result says how it was done, whether your focused window and workspace were the same before and after, and, for a control that carries a value, what the accessibility tree read back:
pressed check box 'Agree' through its accessibility action (no pointer, the human's focus untouched) in yad; now: checked=true
typed 12 characters into the text field in yad through the accessibility interface (the human's focus untouched); the field now holds the typed text (12 characters)
sent ctrl+a to 0x5648592451c0 (yad) with sendshortcut, to the control the app has focused (the human's focus untouched)A press on a check box or slider that the app ignored reads no change seen. A button press, a focused field or keys sent with sendshortcut carry no value to read back, so check their effect with ui. If your focused window changed during the action (because the app brought a window forward, or because you switched), the result ends with a WARNING naming the window that has focus now. Typed results never repeat the text, since the journal keeps every result line and typed text is only ever recorded as a length plus a digest. Screenshots are not used to confirm anything, because many apps stop drawing while hidden and a hidden window's pixels can be stale; ui shows its current state.
Limits
Only controls the accessibility tree exposes can be pressed in the background, and only with their primary action: a right or double click is refused there. Clicking an arbitrary point in a hidden window would need a compositor plugin or an input seat of its own, which this design avoids. Apps without a tree (terminals, canvas apps, Electron and Chrome without
--force-renderer-accessibility) can still take keys.The accessibility tree tells an app's windows apart by title or size. When neither tells the target from the app's other windows (a second window of a single-instance app with the same title and size, say), or the app's accessibility connection belongs to another process than its window, hypruse cannot be sure which window a control belongs to:
click_uirefuses,keyboardsends keys, which Hyprland aims at the window itself, anduisays its controls may be another window's.A hidden window's
uipoints are where its controls sit inside it, not on your screen, and the screen there shows your own windows.uiends with a note saying so, because apointerclick at those points would land on whatever you are looking at.A GTK 3 app brings its window forward when a field takes focus over the accessibility interface. With Hyprland's
misc:focus_on_activateon, that would switch you to it, so focusing a GTK 3 field is refused then. A per-windowfocus_on_activaterule cannot be seen; the after-check reports it.A character your keyboard layout has no key for (an emoji or CJK on most layouts) can only go in through the accessibility interface. A hidden GTK window does not report which of several text fields has its focus, so in a multi-field form such text is refused before any key is sent, and so is typing into a form with a password field among several, unless
allow_auth=true.For each key,
sendshortcutmoves keyboard focus to the target and back inside one compositor step, so your own typing cannot mix in. Your app does see its focus leave and come back, which most apps ignore; a few close an open menu.sendshortcutis refused for XWayland windows, because Hyprland delivers the key to the focused window instead when both are XWayland.With several keyboard layouts,
sendshortcutworks only while you are on the first one. Hyprland finds each key on the layout in use but the app reads it on the first, so on another layout different characters would arrive, and hypruse refuses instead. Text through the accessibility interface does not depend on the layout.Web pages in the background need the browser bridge, which comes in a later release.
While the session is locked, background actions are refused like all other input.
Every trust layer applies to the background paths: confinement checks the target window, the auth guard refuses a background press or key in an authentication dialog, and typing into a password field the accessibility tree shows needs allow_auth=true (an app with no tree cannot be checked, as in the foreground). You cannot see background work, so for anything unattended set HYPRUSE_BACKGROUND=1: input stays on the agent's workspaces, hypruse's own input never takes your screen (an app the agent launches can, and the result warns), the journal keeps every result with its method, and HYPRUSE_MARK tells you when the agent opens a window.
How it works
agent (Claude Code, or any MCP client)
│ stdio
▼
hypruse
├── hyprctl -j ········▶ desktop state: monitors, workspaces, windows, layers
├── hyprctl dispatch ··▶ focus / move / close / launch / movecursor,
│ and sendshortcut for keys to a hidden window
├── grim ··············▶ screenshots: monitor, window, region
├── D-Bus (AT-SPI) ····▶ accessibility tree: named controls, current
│ values, exact coords (ui / marks / click_ui),
│ and presses and text in the background
├── wtype ·············▶ keyboard (zwp_virtual_keyboard_v1, real XKB keymap)
└── raw Wayland wire ··▶ click & scroll (zwlr_virtual_pointer_v1)Optional binaries gate two more tools: imagemagick draws the numbered
overlay for marks, and wl-clipboard backs the opt-in clipboard tool.
Design decisions:
No ydotool / uinput. That path needs a daemon, udev rules or root, and types US scancodes that break on other layouts. hypruse is just another Wayland client of your compositor, same standing as
wlrctl.No portals.
xdg-desktop-portal-hyprlanddoes not implement the RemoteDesktop portal (InputCapture is capture, not injection), so anything built on libei/portals silently degrades on Hyprland. hypruse doesn't try.Cursor positioning through the compositor's own cursor dispatcher (global logical coordinates, exact on any monitor layout), with only button/axis events on the virtual pointer, sidestepping the known multi-monitor bugs of absolute virtual-pointer motion (hyprwm/Hyprland#6749).
Tools
tool | what it does |
| One-call semantic snapshot: monitors, workspaces, windows (address/class/title/geometry), active window, cursor, and layer surfaces (launchers, bars, notification popups) with a best-effort kind and geometry. A listed layer is one the compositor tracks, not one you can see: transparent and dormant surfaces are reported too, so screenshot when visibility matters |
| Focused monitor, one window by address (with grim 1.5+ on Hyprland 0.54+, even hidden or covered; metadata |
| Native-resolution re-capture around an estimated point (optionally clamped to a window): the precision step before clicking small controls, same metadata contract |
| Read a window's accessibility tree (AT-SPI, GTK/Qt apps that expose one) and return clickable elements by name with exact global coordinates, no screenshot; reports current values too (typed text, slider position, checkbox state); falls back to vision when an app exposes nothing |
| Set-of-Marks capture: the window screenshot with every accessible control drawn as a numbered mark, plus a JSON legend (role, name, current value, exact click point per number); needs ImageMagick for the drawing, degrades to the legend alone without it |
| Click a control by accessible NAME or by a |
| move / click / drag / scroll (discrete wheel notches) in global coordinates. Your real cursor, so by default it is refused where the input would land on a window other than yours |
| Type literal text (unicode-safe) or press app-level combos ( |
| Switch workspace, focus/move/close windows, fullscreen, floating (pure IPC, milliseconds; |
| Start an app, silently on the next of the agent's own workspaces unless you name one (or pass |
| The user's own keybinds, decoded ( |
| Execute a keybind by combo ( |
| Run an ordered list of actions (pointer/keyboard/click_ui/hypr/wait_for) in one call; stops the moment the desktop changes in a way the current step did not expect, so a click/type/enter micro-sequence costs one round-trip instead of several |
| Block on real compositor events (window open/close, workspace change, title change, layer surfaces appearing/closing, urgency, screen sharing on/off) with a match filter and timeout; a filtered wait whose condition already holds (window already gone, workspace already active, layer already mapped) answers instantly with |
| Read or write the text clipboard via |
The acting tools (pointer, keyboard, click_ui, hypr, use_bind, sequence) take an optional then argument that appends the result to the same call, so the agent sees the effect without a second round-trip: then='desktop' adds a fresh semantic snapshot (~20 ms, cheap, best for window/focus changes), then='screenshot' a stable capture (best for visual changes), then='ui' the acted-on window's controls with their current values (a few hundred exact tokens, best after typing or toggling; click_ui reads the window it clicked even if the click handed focus to a dialog, the others read the focused window), then='none' nothing (the default everywhere except sequence, which defaults to 'desktop').
Every tool is also a shell verb (hypruse desktop, hypruse click_ui Save --window 0x...) for agents that run commands instead of MCP, with a skill that teaches them: see Shell verbs and the agent skill.
Features
The tools group into five capabilities, ordered most-reliable-and-cheapest first. An agent that reaches for them in this order is both faster and more accurate, and many tasks never need a screenshot at all.
1. Semantic desktop control (start here)
desktop returns the entire window and workspace tree in one call: every window's address, class, title, and geometry, the active window, the cursor, and any layer surfaces the compositor is tracking (launchers, bars, notification popups). hypr and launch then act on it over IPC in milliseconds: switch workspace, focus/move/close/fullscreen/float a window by address, or start an app.
Use it well: never take a screenshot to find or arrange windows. Read desktop, act on the address you want. launch blocks on the real openwindow event and hands back the new window's address, so there is nothing to poll or guess; it also relocates single-instance apps (browsers) that ignore workspace rules.
2. Click controls by name, no pixels
When an app exposes an accessibility tree (most GTK and Qt apps), you can target controls by name instead of by pixel. ui lists every control with its exact global coordinate, and reports the current value of the controls that carry one: the text in a field, a slider's percentage, a checkbox's state. click_ui resolves a name and clicks it in one call, through the real cursor (so the beacon and every safety guarantee still apply), or, in a window you are not in, through the control's own accessibility action without touching your cursor. marks draws numbered marks over a screenshot with a legend, for when you want to see the options first and then click_ui(mark=N).
Use it well: reach for click_ui name="Save" before estimating any pixel, since it is exact and spends no image. Read a form's state with ui (did the box actually tick?) instead of screenshotting it. An ambiguous name returns the candidates rather than guessing. When an app exposes no tree (terminals, canvas apps, Electron/Chrome without --force-renderer-accessibility) the tool says so, and you fall back to vision.
3. Vision when it matters: the zoom loop
For everything the accessibility tree cannot name, screenshot (monitor, window, or region) and zoom (a native-resolution re-capture around a point) carry a strict coordinate contract, global = geometry + pixel / scale, that stays exact on every monitor and fractional scale.
Use it well: don't guess a small control from a full-screen image. Work coarse-to-fine: screenshot the window, estimate the target, zoom there, re-estimate on the sharp crop, then click. This two-step loop is the research-backed way to hit small targets.
4. Fewer round-trips: the latency lever
For an agent the model calls dominate task latency, not the desktop, so the real speedups are structural. sequence runs an ordered micro-plan (click, type, press enter, wait) in a single call, stopping the moment the desktop changes structurally in a way a step did not intend (a window opening, closing, or moving, an unexpected workspace switch, or a seat-taking launcher or on-screen keyboard; it deliberately ignores bare focus changes and notification popups). then='desktop' | 'screenshot' | 'ui' fuses a fresh view of the result into the acting call itself. wait_for blocks on real compositor events (a window or launcher opening, a title changing, a workspace switch, an urgency hint, screen-sharing starting) instead of sleeping and hoping.
Use it well: collapse a known click/type/enter flow into one sequence. After typing into a form, add then='ui' to read the effect back in a few hundred exact tokens instead of a screenshot. After a launch or a shortcut that opens something, wait_for the event rather than sleeping.
5. Safe delegation: trust layers
hypruse hands an agent your real seat, so it ships the controls to bound what that agent can do. Beyond the always-on approval prompts and the Waybar activity beacon, opt-in env flags narrow what an agent can touch: HYPRUSE_READONLY exposes only the observation tools; HYPRUSE_CONFINE restricts input to the windows the agent launched, or a class/workspace allowlist; HYPRUSE_AUTH_GUARD (on by default) refuses to drive authentication dialogs; HYPRUSE_STRICT refuses to act if you took the seat back; HYPRUSE_MARK tags agent-owned windows and announces when the agent opens a window or captures the screen. Two more record rather than restrict: HYPRUSE_JOURNAL writes an auditable NDJSON line per tool call, refusals included, and HYPRUSE_DRYRUN runs every check and delivers nothing, so you can watch an agent plan the work before it touches your desktop.
Use it well: run read-only for the first week. When you trust a workflow, allowlist its tools and, if you want to walk away, confine the agent to a scope so it cannot click or type into your password manager on another workspace. Keep a panic bind handy (hypruse stop, or pkill -f hypruse). The Security model has the full story.
Shell verbs and the agent skill
Not every agent speaks MCP, and the ones that do increasingly prefer a command line: a tool list costs a few thousand tokens per session before the first call, a shell verb costs nothing until it runs. So the same fifteen tools are verbs, going through the same functions the MCP server registers, with the same trust guards, journal and activity beacon:
hypruse desktop # one line per monitor, workspace, window, layer
hypruse launch --workspace 2 -- firefox --new-window https://example.org
hypruse ui --window 0x55a4479a1200 --name Save # [0] push button "Save" @1204,88
hypruse click_ui Save --window 0x55a4479a1200 --then ui
hypruse screenshot --window 0x55a4479a1200 # a file path, then {"geometry":[x,y,w,h],"scale":1.0,...}
hypruse zoom 1180 840 --window 0x55a4479a1200
hypruse keyboard type "hello" --window 0x55a4479a1200
hypruse wait_for title_change --match Inbox --timeout 10
hypruse sequence '[{"op":"click_ui","name":"Search","window":"0x55a4479a1200"},{"op":"keyboard","action":"type","text":"btop","window":"0x55a4479a1200"},{"op":"keyboard","action":"key","keys":"enter","window":"0x55a4479a1200"}]'The contract is built for a program reading the output: the verbs are the tool names, a tool's action is a positional sub-verb (pointer click 800 60, hypr workspace 3, clipboard read), output is compact plain text (one line per fact, --json for the raw result as one line), a capture prints its file path and coordinate metadata rather than bytes, and errors are one line on stderr with a meaningful exit code: 0 delivered, 1 error, 2 usage, 3 refused by a trust layer (or by read-only mode), 4 ran but found nothing to act on (a wait_for timeout, no accessibility tree, an ambiguous name). hypruse --help lists every verb and hypruse <verb> --help its flags; --dry-run rehearses an acting verb. A verb starts in a few hundred milliseconds: the MCP stack is never imported on that path.
Between one-shot processes hypruse keeps the little state a verb would otherwise lose in $XDG_RUNTIME_DIR/hypruse/cli-state.json, keyed by the compositor instance: the marks numbering (so click_ui --mark N works), the launched confinement set, and the HYPRUSE_STRICT seat baseline, which is the one that would otherwise fail open.
The skill that teaches an agent the verbs, the desktop-first workflow and the safety rules ships inside the package. Install it into the skill directories of the agents on your machine (Claude Code, Codex, Pi, Hermes, OpenClaw, OpenCode, Gemini, Antigravity, Cursor, Copilot), or via the skills CLI:
hypruse skill install # ~/.agents/skills/hypruse, linked into each agent that is installed
hypruse skill install --agent codex # one agent, created if absent
npx skills add IlyasKhallouki/hypruse -ghypruse init offers the same install. The skill pre-approves only the observation verbs, doctor, --help and reading the capture files; acting verbs stay behind your agent's own approval prompt, which is the boundary the Security model leans on.
Security model
Read this section before installing. hypruse hands an agent your mouse, your keyboard, your screen contents, and an app launcher. The layers that keep that sane:
Approval: MCP clients gate tool calls. In Claude Code, allowlist the read-only tools (
desktop,screenshot) and leavepointer/keyboard/hypr/launchon ask-first until you trust a workflow.Visibility: the server maintains an activity beacon (
$XDG_RUNTIME_DIR/hypruse/state.json); the shipped Waybar module is invisible when idle and shows a robot indicator while an agent has hands on your desktop.Interruption: click the indicator, or bind a panic key. The portable form works for every install:
bind = SUPER SHIFT, BackSpace, exec, pkill -f hypruse. Ifhypruseis on your PATH (the AUR or a pipx install),bind = SUPER SHIFT, BackSpace, exec, hypruse stopis nicer: it signals the server to shut down gracefully, releasing any held pointer button and clearing the beacon. For auvxinstall useexec, uvx hypruse stop; for a source checkout,exec, uv run --directory /path/to/hypruse hypruse stop. Killing it mid-action is safe either way: button press/release pairs never span tool calls, and even a long drag's held button is released on the way out.The seat is shared. There is one cursor and one keyboard focus, and Hyprland's focus-follows-mouse means a cursor move alone can retarget keystrokes. Don't type while an agent is driving your window; watch the indicator. Background mode keeps the agent off your seat for every window you are not in.
Scope: stdio only (no network listener), nothing persisted except the beacon and the capped screenshot cache in
$XDG_RUNTIME_DIR(tmpfs, newest 20) and, if you turn it on, the action journal on disk under$XDG_STATE_HOME(rotated, one generation, and text-redacted by default). No clipboard access unless you opt in:HYPRUSE_CLIPBOARD=1registers aclipboardtool (never in read-only mode); clipboards hold passwords, so leave it off unless a workflow needs it. A screenshot sees everything visible, and a window screenshot also reaches windows on hidden workspaces, in scratchpads and under other windows: treat an agent session like sharing your whole desktop. Read-only mode andHYPRUSE_CONFINElimit what the agent can do, not what it can see. Window screenshots are refused while the session is locked.What the agent reads is untrusted. Window titles, accessibility names and values, and clipboard text flow verbatim into the agent's context, and any web page, filename, or document can put instructions there (prompt injection). hypruse cannot sanitize meaning, so the approval layer is the backstop: keep consequential tools (
launch,keyboard,clipboard) on ask-first when the agent will look at untrusted windows, and treat "the screen told me to" as attacker input when reviewing an approval prompt.Input never lands where it silently would not work. Three always-on checks (no env flag) refuse or annotate rather than report a phantom success: a click aimed under a launcher or on-screen keyboard layer surface (which sits above windows and would swallow it), typing while a launcher holds the keyboard grab, and any input while the session is locked. A lock screen is an
ext-session-lockclient, invisible to the window and layer lists, so hypruse asks Hyprland itself (hyprctl locked), which covers hyprlock, swaylock, Omarchy's built-in lock, and a locker that crashed and left the session locked. While locked,pointerand a window-lesskeyboardrefuse unlessallow_auth=truesays a human wants the agent driving the unlock prompt (never underHYPRUSE_CONFINE);keyboardwithwindow=andclick_uialways refuse, since input aimed at a window cannot reach it behind the lock. These are truthfulness aids, not a sandbox: the lock check fails open on an unreadable system state, so they harden the common case without being a boundary you can lean on. (WhileHYPRUSE_AUTH_GUARDis on, an unreadable layer list makespointer,click_uiandkeyboardrefuse, since an authentication prompt cannot be ruled out.)
Optional confinement
Seven opt-in env flags. The first five narrow what an agent can touch, and each fails toward less action; the last two record and rehearse rather than restrict. All compose with the layers above:
HYPRUSE_CONFINErestricts input to a scope of windows:launched(only windows hypruse itself opened this session),class:firefox,kitty, orworkspace:3,special:notes. Keyboard,click_ui, andhyprwindow ops are refused outside the scope; apointerclick is refused when any window under the point is out of scope (Hyprland's window list is not z-ordered, so hypruse fails closed rather than guess which window is on top). This is what lets you leave an agent working while your password manager sits on another workspace, out of reach of its clicks and keys (not of its screenshots).use_bindis refused outright while confinement is set, because a keybind runs an arbitrary compositor action that cannot be scoped to a window.HYPRUSE_BACKGROUND=1is the background guarantee: input is confined to the windows on the agent's own workspaces (and toHYPRUSE_CONFINE's scope too, when both are set), and any hypruse action that would take your cursor, focus or workspace is refused. It cannot bound what a command started withlaunchdoes.HYPRUSE_AUTH_GUARD(default on) refuses to click or type into a system authentication dialog (polkit agents, whether a window like hyprpolkitagent or a prompt the shell draws as a layer, as Omarchy 4 and end-4's dots do; the GNOME keyring prompt; Hyprland's own dialogs, which are its permission prompt and also its app-not-responding and safe-mode notices, since all three share one window class), so a manipulated agent cannot approve a privilege escalation.click_uialso refuses when such a dialog floats over the control it was asked to click. When the layer list cannot be read, it refuses rather than guess. A prompt a shell opens as an ordinary window of its own class, as DankMaterialShell does, is not recognised. SetHYPRUSE_AUTH_GUARD=strictto also refuse typing into a password field inside an ordinary window (a browser login), detected via the accessibility tree. A per-callallow_auth=trueonpointer/keyboard/click_uioverrides it, and because it changes the tool's arguments the override surfaces distinctly in the approval prompt.HYPRUSE_AUTH_GUARD=0disables it.HYPRUSE_STRICTrefuses to act when the cursor or focused window moved since hypruse's last action (the human, or a popup, took the seat): the agent must re-readdesktop/screenshotand retry, so it never types into a window you just switched to.HYPRUSE_MARKmakes the agent's presence legible on the desktop: it tags every window the agent openshypruse-ownedand flashes an on-screen notice when the agent opens a window or captures the screen. It also installs aborder_colorwindow rule on that tag so owned windows get a colored outline, but whether a runtime rule renders depends on your Hyprland version and config precedence (on some setups it does not take effect); when it cannot be installed at all, hypruse says so on stderr rather than leaving you with a marking layer that is quietly not running. For a guaranteed outline, add the rule to your own config, which hypruse's tagging then matches:windowrule = border_color rgb(ff5555), tag hypruse-ownedinhyprland.conf(older Hyprland:tag:hypruse-owned), orhl.window_rule({ match = { tag = "hypruse-owned" }, border_color = "rgb(ff5555)" })inhyprland.lua.HYPRUSE_JOURNALrecords what the agent did: one NDJSON line per tool call in$XDG_STATE_HOME/hypruse/journal.ndjson(HYPRUSE_JOURNAL=1), or a path of your own. Read it withhypruse journal, re-run it withhypruse replay. See The record below.HYPRUSE_DRYRUNis a rehearsal: every argument check and every guard above runs, then the call reports what it would have done and delivers nothing.
The record: journal, dry run, replay
The flags above decide what an agent may do in the moment and then forget it happened. HYPRUSE_JOURNAL is the memory. One JSON object per line, so tail -f, grep, and jq all work on a live file:
{"v":1,"seq":7,"ts":"2026-08-02T09:12:13.456Z","kind":"act","tool":"pointer",
"args":{"action":"click","x":800,"y":60},"outcome":"ok","ms":37,"result":"click ok"}kind splits the two questions people actually ask: act is input delivered to your desktop, observe is the agent looking, which is what a privacy audit wants (when the screen was captured, when the clipboard was read). Observation results are never recorded, only that they happened, so the journal never becomes a second copy of everything the agent saw. Refusals are recorded too, with the guard's own message: it is the only place the history of your trust layers doing their job exists.
Typed and copied text is recorded as a length plus a short digest, not as text, because keystrokes are passwords. HYPRUSE_JOURNAL_TEXT=1 keeps it verbatim, which you need only to replay typing. Note what a digest is and is not: it proves two entries typed the same thing and it will not hand a reader your password, but it is an unsalted SHA-256 prefix next to an exact character count, so a four-digit PIN is trivially recovered from it. Treat the journal as sensitive either way. It is written 0600 in a 0700 directory, and rotated at HYPRUSE_JOURNAL_MAX_BYTES (8 MiB, one previous generation kept as .1; set 0 to never rotate).
The journal is a recorder, not a guard: if it cannot be written the action still happens and hypruse warns once on stderr, because failing your desktop over a log line is the wrong trade. What it does not record is a then= observation as its own entry: the acting call that carried it is recorded, then=screenshot and all, but the capture does not get a second line of its own.
Read it back with hypruse journal (--acts for actions only, --refused for what the guards stopped, -n N to tail, -v to include each result):
1 09:12:10 session start pid 4211 0.10.0 confine=launched auth_guard=1 strict=True
14 09:12:13 act pointer action=click x=800 y=60
16 09:12:15 act keyboard action=type text=<11 chars>
19 09:12:19 act hypr action=close_window target=0x5f2a10
REFUSED TrustError: 0x5f2a10 (Signal) is outside the agent's confinement scope
312 actions (0 dry), 604 observations, 1 refused by a trust layer, 0 errorsHYPRUSE_DRYRUN=1 turns the same session into a rehearsal. Every acting tool validates its arguments and runs every trust guard, then reports the plan instead of executing it, so a dry run refuses exactly what a real run would:
DRY RUN, nothing was delivered: would click push button 'Send' at (1204, 880) in signalNothing reaches the desktop: not the click, not the keystroke, not even the window focus that normally precedes typing. Enforced twice, once at each tool and once at the input path itself, so a code path nobody thought of fails loudly rather than quietly acting during a simulation. The agent is told dry run is on, so it reports a plan instead of retrying an action that "did not work". The scope is the agent's actions, not the server's own startup: HYPRUSE_MARK, if you set it, still installs its window rule when the server starts.
hypruse replay <journal> re-issues a journal's actions through the same tool functions, so the same guards apply to the replay. It prints the plan and stops there unless you pass --execute. Before it takes the seat it refuses outright, rather than failing halfway and leaving your desktop part-way through someone else's plan, when: an action was recorded by a newer hypruse, a recorded window no longer exists (--skip-missing runs the rest), typed text was recorded as a digest, the entry is a click_ui(mark=N) whose numbering died with the session that drew it, the entry is a clipboard write and HYPRUSE_CLIPBOARD is not set, or HYPRUSE_READONLY or HYPRUSE_DRYRUN is set. It paces itself from the recorded timing, capped by --max-gap and scaled by --speed, and its own actions are recorded and marked, so replaying the same file again runs the original plan rather than the plan plus the replay of it.
The honest limit is window addresses: they are heap pointers, so yesterday's journal mostly names windows that are gone, and an address can even be reused by a different window later, which no pre-flight can catch. Replay is for re-running a flow on a desktop that still looks like the one recorded.
Dry run and replay compose in the obvious direction: let the agent work with HYPRUSE_DRYRUN=1, read the journal, and replay it with --execute once the plan is one you like.
Performance
Measured on a live session (Hyprland 0.55, 1080p, 20 windows): desktop
~20 ms (one batched hyprctl call), workspace/window dispatch ~10-20 ms, full-monitor screenshot ~65 ms
(fast JPEG default; ~800 ms if you ask for lossless PNG, grim's zlib
path dominates), region/zoom captures well under that. If tool
calls feel slow, it is almost certainly the MCP approval prompt in
front of each call, not the server. Allowlist the tools you trust and the
latency disappears. Claude Code (.claude/settings.json):
{
"permissions": {
"allow": [
"mcp__hypruse__desktop",
"mcp__hypruse__screenshot",
"mcp__hypruse__hypr"
// add pointer/keyboard/launch once you trust your workflows
]
}
}Coordinates
Everything speaks Hyprland's global logical coordinates, the space hyprctl cursorpos and window at use. Screenshots are pixel-space; each capture returns geometry and scale so global = origin + pixel / scale. On scale 1.0 monitors (most setups) image pixels are global coordinates.
The zoom tool does the precision arithmetic for the agent: give it an estimated global point and it captures a native-resolution box around it, clamped to the screen (or to a window), with the same metadata contract. That two-step loop, estimate on the full view then re-estimate on the zoom, is the research-backed way to hit small controls.
Captures default to JPEG q90: on a 1080p frame that is roughly 12x faster to encode than PNG (grim's zlib path dominates capture time, measured ~65 ms vs ~800 ms) and 3-4x smaller, while full-res q90 reads UI text well. Pass lossless=true for exact pixels (PNG). In image mode, captures also fit the host's result-size limit (Claude Desktop caps tool results at 1 MB) by degrading quality before resolution, since grim's downscale filter is slower than a full-res capture, and cap the long edge at HYPRUSE_MAX_IMAGE_EDGE pixels (default 1568) so the host never downscales the image under the model. The applied scale is folded into the returned metadata, so coordinate mapping stays exact; tune with HYPRUSE_MAX_IMAGE_BYTES, or pass scale for a deliberate zoom-out.
By default the screenshot tool writes the image under $XDG_RUNTIME_DIR/hypruse/ and returns its path; MCP hosts with a file reader (Claude Code's Read) render it natively. This default exists because some hosts (including Claude Code 2.1.x) serialize inline MCP image blocks to base64 text the model cannot see. HYPRUSE_SCREENSHOT_MODE=image switches to inline image content blocks for hosts that render them correctly.
Development
uv sync --group dev
uv run pytest # unit tests, no compositor needed
uv run pytest -m e2e --override-ini addopts= # live seat-safe checks
uv run pytest -m background --override-ini addopts= # live: drives yad forms on the agent's workspaces
uv run python scripts/e2e_input.py # supervised: takes the seat ~10sThe background suite opens yad forms on the agent's workspaces, drives them in the background, and checks after every step that your active window, workspace and cursor are exactly as they were, so leave the mouse and keyboard alone while it runs. It also checks Hyprland's own events, which hold even while you work: no window it opened ever takes focus, and no agent workspace is switched to.
The input e2e is deliberately manual: it borrows your cursor and keyboard, counts down, proves click/scroll/type delivery by reading the target terminal's screen back over kitty remote control, and restores your focus.
scripts/vm/ builds an Omarchy test VM, and its scripts run only when you start them yourself: fetch downloads the Omarchy ISO from iso.omarchy.org and its signing key from GitHub, shell --bootstrap serves a setup script to the VM on 127.0.0.1 until ssh works, and check installs hypruse from the AUR inside the VM. scripts/vm/README.md has the details. The plugin never runs anything under scripts/.
Roadmap
Grounded in measured hot-path latencies and the finding that LLM calls are 76 to 96% of computer-use task latency (OSWorld-Human), so cutting round-trips beats shaving milliseconds. The round-trip work that framing motivated has largely shipped: sequence, act-and-observe then= (including then='ui'), and the accessibility-tree tools (ui, marks, click_ui) that target controls by name with no screenshot. What remains:
Faster
In-process wlr-screencopy over the raw wire (as input already works): drop grim's fork floor from small captures and add damage-tracked wait-for-stable that returns the instant the screen settles.
Fewer round-trips
Semantic screen diff: after an action, return only what changed (window topology from the event stream, or a bounded changed-region crop) instead of a full frame. The socket2 event expansion behind
wait_foralready tracks most of the topology; the missing piece is folding it into a post-action delta.
Deeper reading
Wider accessibility coverage: close the gaps the
uiandmarkstools hit today, chiefly GTK's newer combo boxes that publish neither their text nor selection (so a rendered dropdown value still needs a screenshot), plus AT-SPI value-change events sothen='ui'can report a control settling without a poll.Notifications: read recent desktop-notification content and history, not just wait for the popup to appear (
wait_foralready matcheslayer_openon the notification namespace).
Background
Web pages in the background, through the browser bridge (an extension and a native messaging host).
Trust
recordtool: a scoped GIF or mp4 of the agent driving the desktop, via wf-recorder (a wlroots-family binary like grim), a visual companion to the journal.
Platform
sway / niri support: the wire client already speaks the wlr protocols; what remains is an IPC layer alongside
hyprctl.py(contributions welcome).Headless end-to-end tests in CI: needs a QEMU virtio-gpu VM, since Hyprland's aquamarine backend requires a real GPU render node that hosted runners lack.
Measurement
Zoom-loop precision benchmark: measure click accuracy of the coarse-to-fine loop against known targets.
End-to-end task-success benchmark on Hyprland (OSWorld-style): the deferred bigger sibling of the zoom-loop microbenchmark, scoring full multi-step tasks through the real MCP surface so the a11y-versus-vision and round-trip work is judged on task completion, not latency alone.
Related projects
project | approach | on Hyprland |
computer-use-linux | AT-SPI + portals, ydotool fallback | GNOME-first, and the RemoteDesktop portal it prefers is not implemented by xdg-desktop-portal-hyprland; since 2026-10-31 it has an opt-in Hyprland background mode ( |
agent-desktop (Vercel) | computer use CLI for agents; AT-SPI on Linux | as of 2026-11-08, keys, display layout and window control refuse on Hyprland because the Linux adapter measures only Mutter's interfaces (#386) |
hyprmcp | hyprctl wrapper | window management only; no screenshots or input |
wayland-mcp | evemu input, VLM analysis | requires elevated setup for input; no Hyprland semantics |
Anthropic computer-use-demo | X11 + xdotool in Docker | a sandboxed reference environment rather than a live desktop |
Cua (cua-driver) | cross-platform driver; an optional Hyprland compositor plugin gives the agent its own input seats | the plugin must be built for the exact installed Hyprland version, its README calls it experimental and unreleased, and as of 2026-11-08 it does not yet support Hyprland 0.57's input route (#6232) |
Research
hypruse ships no OCR engine; its universal precision mechanism is the coarse-to-fine zoom loop: screenshot a window, re-capture the target region at native resolution, click through the exact coordinate mapping. That choice follows what the GUI-agents field converged on. Anthropic's computer use grounds clicks from raw pixels and ships a zoom action as the documented fix for small text; its troubleshooting guidance for near-miss clicks prescribes zooming and region cropping, never OCR [1]. OpenAI's CUA is likewise pure pixel grounding under resolution discipline, with no OCR layer at all [2]. Zoom is also the measured lever: training-free iterative zooming roughly doubles high-resolution grounding accuracy (OS-Atlas-7B, 18.9 → 49.7 on ScreenSpot-Pro) [3], and the benchmark's official harness implements a dozen grounding-model adapters plus four zoom/crop strategies, but zero OCR baselines [4]. Vision-only agents match or beat agents that additionally consume HTML or accessibility trees [5], substrates Wayland doesn't guarantee anyway, and state-of-the-art native agents run from screenshots alone [7]. OCR was rejected because it is blind to icons, the element class every grounding model handles worst (SeeClick: 30-52% on icons vs 56-78% on text) [6]; where OCR survives in modern stacks it is a text-disambiguation sidecar, not the targeting mechanism [8].
Where an app exposes an accessibility tree, hypruse also reads it (the ui tool, AT-SPI over D-Bus) to target controls by name with exact coordinates and no screenshot. This follows the strongest Linux precedent: OSWorld, the standard computer-use benchmark, exposes the desktop accessibility tree (obtained on Ubuntu through AT-SPI) as a first-class observation alongside screenshots, and reports the accessibility-tree-plus-screenshot combination as its best configuration [9]. The tree gives exact element identity and coordinates that current models cannot reliably infer from pixels: Agent-S tags each element with an id because MLLMs "lack an internal coordinate system," lifting OSWorld success from 11.2 to 20.6 percent [10]; Microsoft's UFO drives Windows through the UI Automation tree and fuses it with vision [11]; browser agents read the accessibility tree, which Playwright serializes to compact YAML, rather than pixels for the same reason [12]. hypruse's Wayland-specific trick is coordinate mapping: AT-SPI screen coordinates are unreliable on Wayland because an app does not know its global position, so hypruse uses window-relative extents plus the window position it already has from hyprctl. Coverage is uneven by nature: canvas, games, terminals, and Electron/Chrome without a flag expose little or nothing [13]. Testing this implementation against real GTK and Qt apps sharpened that in both directions: a typed entry reads back its exact contents, and sliders and toggles report their position and state, but GTK's newer combo boxes publish neither their text nor a selection, so reading a rendered dropdown value still needs a screenshot. Toolkits also describe widgets they never laid out (zero-height scroll arrows, unrendered tab pages reporting origins in the millions), which hypruse rejects against the window rect hyprctl knows authoritatively. A strong visual grounder can substitute for the tree entirely [5], so the accessibility tree complements the zoom loop rather than replacing it, and vision stays the guaranteed fallback.
Anthropic, Computer use tool: platform docs (
computer_20251124,enable_zoom, resolution guidance)OpenAI, Computer-Using Agent and the computer use guide
DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning, EMNLP 2025. arXiv:2507.00008
Li et al., ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use. arXiv:2504.07981; official harness
Gou et al., Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents (UGround), ICLR 2025 Oral. arXiv:2410.05243
Cheng et al., SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents, ACL 2024. arXiv:2401.10935
Qin et al., UI-TARS: Pioneering Automated GUI Interaction with Native Agents. arXiv:2501.12326
Agyeya et al., Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents (Tesseract as a textual-grounding sidecar). arXiv:2504.00906
Xie et al., OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. arXiv:2404.07972; the a11y tree is obtained on Ubuntu through AT-SPI (code)
Agashe et al., Agent S: An Open Agentic Framework that Uses Computers Like a Human. arXiv:2410.08164
Zhang et al., UFO: A UI-Focused Agent for Windows OS Interaction (UI Automation + vision). arXiv:2402.07939
Playwright, ARIA snapshots: the accessibility tree as compact structured text
Wang et al., GUI Agents: A Survey (accessibility-API coverage gaps; a11y complements vision). arXiv:2412.13501
License
Available Tools
14 toolsbindsARead-only
The user's own Hyprland keybinds: combo, action, arg, and a
description when the config provides one. This is how the desktop's
owner drives it: to perform one of these workflows, call use_bind
with the combo (it runs the bound action). An action of lua means the
bind is a closure in a Lua Hyprland config, which nothing can run from
outside: read its description and do the same thing with hypr or
launch. NOTE: the keyboard tool canNOT trigger these compositor
binds (synthetic keys reach apps, not Hyprland's bind matcher), so do
not try to press them.
Inputs: no named parameters. Returns: result
click_uiADestructive
Click a control by its accessible NAME, or by a mark number from
the last marks capture, in ONE call: the control comes from the
accessibility tree, so no screenshot and no pixel estimation is spent.
On the window the human is in, the window is focused and the click
goes through the real pointer (visible cursor, same panic-kill
guarantees). On any other window it runs in the background: the
control's accessibility action presses it (a text field gets the app's
own focus), the human's cursor and focus stay put, and the result reads
the control back; a control with no action is refused there. When no
control matches, a name also finds an element in another role that has
an action (a web app's list row); if its action only focuses it, the
result says so and whether the app reports it focused, which does not
show what a key sent next will do: check with ui.
background true or false forces one way (false takes over the human's
screen). Pass exactly one of
name (matched against window's controls, exact accessible name
preferred, substring otherwise) or mark. An ambiguous name returns
the candidates instead of guessing: disambiguate with index (0-based
into that list) or a more specific name. Falls back with a note when
the app exposes no tree (use screenshot + zoom + pointer then).
then ('desktop'|'screenshot'|'ui'|'none') appends the result;
'ui' shows the click's effect on the controls in the same call.
allow_auth=true overrides the refusal to click a system
authentication dialog.
Inputs: mark, name, then, index, +5 more. Returns: result
desktopARead-only
Semantic desktop snapshot: monitors, workspaces, windows (address,
class, title, at + size in global coords), active window, cursor,
and layers: launchers (wofi/rofi), bars, notification popups, and
on-screen keyboards are NOT windows and appear only there, with a
best-effort kind and global geometry you can screenshot by region or
click into. A listed layer is one the compositor tracks, not one you
can see: it may be transparent or dormant, so screenshot when
visibility matters. Call first; act on the addresses it returns.
Inputs: no named parameters. Returns: object
hyprADestructive
Window/workspace ops over IPC (instant, no vision).
action='workspace' (workspace: number/name/'special:name') |
'focus_window' (target: address) | 'move_window' (target + workspace,
silent) | 'close_window' (target) | 'fullscreen' (target?) |
'toggle_floating' (target?). then ('desktop'|'screenshot'|'ui'|'none')
appends the result to this call. While the background guarantee is on
(HYPRUSE_BACKGROUND=1), workspace, focus_window and fullscreen are
refused because they change the human's view, and move_window moves
only to the agent's own workspaces.
Inputs: action (required), then, target, workspace. Returns: result
keyboardADestructive
Keyboard to an app. action='type' (text, unicode-safe) |
'key' (keys combo: 'ctrl+shift+t', 'esc', 'F5'; aliases
enter/esc/tab/backspace/pgup/pgdn/arrows, else XKB keysyms). Pass
window (an address from desktop) so keystrokes land in the intended
app rather than whatever currently holds focus. The window the human
is in is focused and typed into on their screen. Any other window gets
the keys in the background, with the human's focus left alone: text
goes into its text field through the accessibility interface, or key
by key through Hyprland's sendshortcut (a character the keyboard layout
has no key for is refused on that path). Keys sent that way, and key
combos, go to the control the app itself has focused, which is not the
field text went into through accessibility: focus a field first with
click_ui. Without window, keys go to
the focused window. background true or false forces one way. This
drives shortcuts the focused application handles
(ctrl+t, ctrl+l). It does NOT trigger Hyprland's own keybinds
(super+...): those go through use_bind, and workspace/window actions
through hypr. then ('desktop'|'screenshot'|'ui'|'none') appends the
result to this call. allow_auth=true overrides the default refusal to
type into a password field or a system authentication dialog (only when
a human intends that credential entry).
Inputs: action (required), keys, text, then, +3 more. Returns: result
launchADestructive
Open an app: run command via Hyprland exec. Optional workspace placement
(silent, works even for single-instance apps like browsers, whose
window gets moved after it appears) and wait_s (1-30, default 8;
raise for slow apps). Without workspace, the app opens silently on
the next of the agent's own workspaces (HYPRUSE_AGENT_WORKSPACES, 99
down to 90 by default) that is not on screen, so the agent can work on
it in the background; background=false opens it on the human's
workspace instead. It waits for its own window (one on that workspace,
or of the program's own class), never one the human opens meanwhile.
An app that is already running opens its window from the running
process, on the human's screen, before it is moved: the note says so.
Returns the new window's address/class/title/workspace, or a timeout
note.
Inputs: command (required), wait_s, workspace, background. Returns: result
marksARead-only
Set-of-Marks capture: a screenshot of the window WITH its accessible
controls drawn as numbered red marks, plus a JSON legend mapping each
number to the control's role, name, current value, and exact global
click point. One glance replaces the estimate-zoom-estimate loop for
every control the accessibility tree knows: read the number off the
image and call click_ui(mark=N) (or pointer at the legend's x,y).
window is an address from desktop (default: focused); name filters
the marked controls. Falls back to the plain legend when ImageMagick is
not installed, and to a fall-back-to-vision note when the app exposes
no tree (then use screenshot + zoom).
Inputs: name, window. Returns: result
pointerADestructive
Mouse in global coordinates. action='move' (x,y) | 'click' (optional
x,y first; button left/right/middle; double=true) | 'drag' (x,y →
to_x,to_y holding button) | 'scroll' (scroll_dy notches, positive =
content down; optional x,y first). then appends the result to this
call so you skip a round-trip: 'desktop' a fresh snapshot, 'screenshot'
a stable capture, 'ui' the focused window's elements with current
values, 'none' (default) nothing. allow_auth=true overrides the
refusal to click over a system authentication dialog. The pointer is
the human's own cursor, so it never runs in the background: it is
refused where the input would land on a window other than the one the
human is in (press controls there with click_ui), unless
background=false.
Inputs: action (required), x, y, then, +8 more. Returns: result
screenshotARead-only
Capture the focused monitor, a window (window: "active" or an
address from desktop, cheapest for reading one app), or a region
"x,y,WxH". Returns the image (or a file path to read) + JSON metadata
with geometry/scale for pixel→global mapping. A window on a hidden
workspace or under another window is still captured as itself
(metadata source "window"; without grim -T a shown window is cropped
from the screen, source "screen", and a hidden one is refused);
visible says whether the compositor draws it, and
a hidden one may show how it last looked (many apps stop drawing while
hidden). Window captures are refused while the session is locked. scale 0.1-1.0:
optional deliberate downscale, usually leave unset. stable=true
waits (up to 2s) until two consecutive frames match, so a capture
right after an action is not taken mid-animation; metadata gains
stable. Captures are fast JPEG by default; lossless=true returns
PNG for pixel-exact work. Before clicking a small control, follow with
zoom at the estimated point.
Inputs: scale, region, stable, window, +1 more. Returns: result
sequenceADestructive
Run an ordered list of actions in ONE call, so a click/type/enter
micro-sequence costs one round-trip instead of several. Each step is
{"op": "pointer"|"keyboard"|"click_ui"|"hypr"|"wait_for", ...that tool's
args}, e.g. [{"op":"pointer","action":"click","x":800,"y":60},
{"op":"keyboard","action":"type","text":"hello","window":"0x.."},
{"op":"keyboard","action":"key","keys":"enter"}]. With stop_on_change
(default) the run stops, best-effort, when it notices a STRUCTURAL
change between steps that the step did not intend: a window opening
(e.g. a dialog), closing, or moving, a switch to an unexpected
workspace, or a seat-taking layer surface (a launcher or on-screen
keyboard) appearing, so later steps do not act on stale state.
Notification popups and bars are not treated as changes. It does NOT catch
a bare focus change, so to type into a specific window reliably give
that keyboard step a window= address (the keys go to that window).
Bounded to 20
steps and ~30s total. then observes the final state ('desktop'
default, 'screenshot', 'ui', 'none'). background applies to every
pointer, keyboard and click_ui step that does not set its own, and
background=true refuses a hypr step that takes the human's view.
Inputs: steps (required), then, background, stop_on_change. Returns: result
uiARead-only
Read a window's accessibility tree (AT-SPI) and return its elements
with GLOBAL click points, so you can target a control by NAME with no
screenshot and no pixel guessing. window is an address from desktop
(default: the focused window). name filters to elements whose
accessible name contains it (case-insensitive); actionable (default)
keeps only interactive roles (buttons, entries, menu items, ...); with
a name that matches none of those, it keeps named elements in other
roles that have an accessibility action (a web app's list row), with
the action's name as action.
Returns [{role, name, x, y, clickable}] where x,y is the click point:
focus the window, then click it with pointer (the window must be
visible to receive the click, and focusing can move it, so read again
after focusing), or do both in one call with click_ui.
Controls that carry a CURRENT VALUE also
report it: value (text typed into an entry, or a slider/spinner
number), percent for a slider's position, checked for a box or
toggle. Password fields never report contents, and many dropdowns
expose no value at all, so read the screen with screenshot when a
rendered value matters. Not every app exposes a tree (terminals, and
Electron/Chrome without --force-renderer-accessibility, expose little
or nothing); when it does not, fall back to screenshot + zoom.
Inputs: name, window, actionable. Returns: result
use_bindADestructive
Run one of the user's own Hyprland keybinds by its combo (from the
binds tool), e.g. 'SUPER+F'. This executes the bound action directly
(the only reliable way: synthetic keypresses do not trigger compositor
binds). Use it to drive the owner's configured workflows: launchers,
layout shortcuts, scratchpads. then ('desktop'|'screenshot'|'ui'|'none')
appends the result to this call (handy after a launcher bind). Refused
while HYPRUSE_CONFINE is set or the background guarantee is on
(HYPRUSE_BACKGROUND=1): a bind runs an arbitrary compositor action
that cannot be scoped to a window.
Inputs: combo (required), then. Returns: result
wait_forARead-only
Block until a desktop event happens (real compositor events, not
polling). event: 'window_open' | 'window_close' | 'workspace' |
'title_change' | 'layer_open' | 'layer_close' (layer-shell surfaces:
launchers, notification popups; match on the namespace, e.g. 'wofi') |
'urgent' (a window demands attention) | 'screencast' (screen sharing
started/stopped). match: optional case-insensitive substring filter
over the event's fields (class/title/workspace name/address/namespace).
timeout_s 1-60, default 10. Returns the event payload, or a timeout
note; a filtered wait whose condition ALREADY holds (the window is
already gone, the workspace already active, the layer already mapped)
returns instantly with already: true instead of missing an event
that fired before it could subscribe. Use it after actions with
delayed effects: app startups, page loads that change a window title,
a launcher bind that pops a layer.
Inputs: event (required), match, timeout_s. Returns: result
zoomARead-only
Native-resolution re-capture around a point: the precision step of
the coarse-to-fine loop. Screenshot first, estimate the target's global
x,y, zoom there, re-estimate on the zoomed image (scale ~1.0, so
global = geometry[:2] + image_pixel), then click. size "WxH" in
logical pixels (default 480x360) is clamped to the screen; window
(an address from desktop, on screen) clamps to that window instead. The metadata
echoes the requested point back as point; stable=true waits for
the frame to settle first; lossless=true returns PNG.
Inputs: x (required), y (required), size, stable, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Each tool has a crisply distinct role, and the descriptions actively delineate boundaries (pointer vs click_ui, keyboard vs use_bind vs hypr, screenshot vs zoom vs marks vs ui). Overlapping-seeming tools like screenshot/zoom/marks and ui/click_ui are separated by explicit coarse-to-fine vs accessibility vs annotated-capture semantics. An agent can reliably pick the right tool.
All names are lowercase single tokens with underscore used consistently for multi-word tools (wait_for, click_ui, use_bind), so formatting is uniform. The only wobble is semantic: some names are nouns (desktop, marks, binds, pointer) and others verbs (launch, zoom), which is a minor deviation from a single predictable pattern.
14 tools is well within the ideal 3-15 range and each earns its place: perception (desktop, screenshot, zoom, ui, marks), input (pointer, keyboard, click_ui), orchestration (wait_for, sequence), and system control (hypr, launch, binds, use_bind) with no filler.
The desktop-automation surface is essentially full: snapshot, capture at two fidelities, accessibility read/annotate, mouse, keyboard, background-window targeting, event waiting, window/workspace IPC, app launch, keybind discovery and replay, plus a batch runner. It even documents fallback paths (vision when no a11y tree) and hard limits (locked session, auth dialogs), leaving no obvious dead ends.
Maintenance
Related MCP Connectors
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn 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.276MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that controls native Wayland windows on KDE Plasma from an AI agent, enabling window listing, screenshots, clicks, typing, and more.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for controlling Linux desktops over Wayland, enabling AI agents to perform mouse, keyboard, window, and screenshot operations on Fedora KDE Plasma.AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceMCP server for controlling Hyprland Wayland compositor: screen capture, mouse/keyboard injection, and automation via native Hyprland IPC and wlr protocols.MIT