hypruse

Name: hypruse
Author: IlyasKhallouki

作者：IlyasKhalloukiバージョン 0.13.0i★ –iパソコンで動く

レジストリ名io.github.IlyasKhallouki/hypruse

インストール

概要

作者による説明（英語の原文）

Computer use for Hyprland: semantic desktop state over IPC, plus vision and native input

PopNx MCPの3つの柱

この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。

利用者の声iレビューはまだありませんレビューは今後のステップで、アカウント機能と一緒に始まります
私たちの基本チェックi1項目中1項目に合格公開情報からチェック。コードはまだスキャンしていません
利用状況i未計測★ –

できること

このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。

接続方法: パソコンで動く
トランスポート: stdio
カテゴリ: その他

インストール

使っているAIアプリを選んで、設定をコピーしてください。

インストールの前に

基本チェック：1項目中1項目に合格
あなたのパソコンで、あなたのユーザーと同じ権限（ファイル、ネットワーク、アプリ）で動きます。
自分で入力するもの： HYPRUSE_SCREENSHOT_MODE, HYPRUSE_READONLY, HYPRUSE_CONFINE, HYPRUSE_AUTH_GUARD, HYPRUSE_STRICT, HYPRUSE_MARK, HYPRUSE_CLIPBOARD, HYPRUSE_JOURNAL, HYPRUSE_JOURNAL_MAX_BYTES, HYPRUSE_JOURNAL_TEXT, HYPRUSE_DRYRUN

必要なもの

PyPIPythonのuvのインストール（uvxコマンドに必要）

どのアプリを使っていますか？

ClaudeClaude CodeCursorVS CodeChatGPT

上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。

Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます

{
  "mcpServers": {
    "hypruse": {
      "command": "uvx",
      "args": [
        "hypruse"
      ],
      "env": {
        "HYPRUSE_SCREENSHOT_MODE": "your-value",
        "HYPRUSE_READONLY": "your-value",
        "HYPRUSE_CONFINE": "your-value",
        "HYPRUSE_AUTH_GUARD": "your-value",
        "HYPRUSE_STRICT": "your-value",
        "HYPRUSE_MARK": "your-value",
        "HYPRUSE_CLIPBOARD": "your-value",
        "HYPRUSE_JOURNAL": "your-value",
        "HYPRUSE_JOURNAL_MAX_BYTES": "your-value",
        "HYPRUSE_JOURNAL_TEXT": "your-value",
        "HYPRUSE_DRYRUN": "your-value"
      }
    }
  }
}

ターミナルでこれを実行します

claude mcp add hypruse --env HYPRUSE_SCREENSHOT_MODE=your-value --env HYPRUSE_READONLY=your-value --env HYPRUSE_CONFINE=your-value --env HYPRUSE_AUTH_GUARD=your-value --env HYPRUSE_STRICT=your-value --env HYPRUSE_MARK=your-value --env HYPRUSE_CLIPBOARD=your-value --env HYPRUSE_JOURNAL=your-value --env HYPRUSE_JOURNAL_MAX_BYTES=your-value --env HYPRUSE_JOURNAL_TEXT=your-value --env HYPRUSE_DRYRUN=your-value -- uvx hypruse

動かす前に、空欄の値を入力してください。

Cursorで開く

または、設定を自分でコピーする

プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます

{
  "mcpServers": {
    "hypruse": {
      "command": "uvx",
      "args": [
        "hypruse"
      ],
      "env": {
        "HYPRUSE_SCREENSHOT_MODE": "your-value",
        "HYPRUSE_READONLY": "your-value",
        "HYPRUSE_CONFINE": "your-value",
        "HYPRUSE_AUTH_GUARD": "your-value",
        "HYPRUSE_STRICT": "your-value",
        "HYPRUSE_MARK": "your-value",
        "HYPRUSE_CLIPBOARD": "your-value",
        "HYPRUSE_JOURNAL": "your-value",
        "HYPRUSE_JOURNAL_MAX_BYTES": "your-value",
        "HYPRUSE_JOURNAL_TEXT": "your-value",
        "HYPRUSE_DRYRUN": "your-value"
      }
    }
  }
}

ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。

VS Codeで開く

または、設定を自分でコピーする

プロジェクトの .vscode/mcp.json に貼り付けます

{
  "servers": {
    "hypruse": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "hypruse"
      ],
      "env": {
        "HYPRUSE_SCREENSHOT_MODE": "your-value",
        "HYPRUSE_READONLY": "your-value",
        "HYPRUSE_CONFINE": "your-value",
        "HYPRUSE_AUTH_GUARD": "your-value",
        "HYPRUSE_STRICT": "your-value",
        "HYPRUSE_MARK": "your-value",
        "HYPRUSE_CLIPBOARD": "your-value",
        "HYPRUSE_JOURNAL": "your-value",
        "HYPRUSE_JOURNAL_MAX_BYTES": "your-value",
        "HYPRUSE_JOURNAL_TEXT": "your-value",
        "HYPRUSE_DRYRUN": "your-value"
      }
    }
  }
}

これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。

選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。

自分で入力する値

HYPRUSE_SCREENSHOT_MODE env
How captures are returned: 'file' writes to XDG_RUNTIME_DIR and returns the path, 'image' returns the image inline. Use 'image' for clients that render MCP images but cannot read files, such as Claud…
HYPRUSE_READONLY env
Set to 1 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.
HYPRUSE_CONFINE env
Restrict input to a scope of windows and refuse everything outside it: 'launched' (only windows hypruse opened this session), 'class:firefox,kitty', or 'workspace:3,special:notes'. Unset means no con…
HYPRUSE_AUTH_GUARD env
Refuse to click or type into system authentication dialogs (polkit, keyring prompts). On by default; 'strict' also refuses password fields in ordinary windows; 0 disables it.
HYPRUSE_STRICT env
Set to 1 to refuse to act when the cursor or focused window moved since hypruse's last action, so the agent must re-read the desktop before retrying.
HYPRUSE_MARK env
Set to 1 to make the agent's presence legible: tag every window it opens 'hypruse-owned' and flash an on-screen notice when it opens a window or captures the screen.
HYPRUSE_CLIPBOARD env
Set to 1 to register the opt-in clipboard tool (never in read-only mode). Off by default because clipboards hold passwords.
HYPRUSE_JOURNAL env
Record every tool call, refusals included, as one NDJSON line: 1 writes to XDG_STATE_HOME/hypruse/journal.ndjson, or give a path. Read it back with 'hypruse journal'. Off by default.
HYPRUSE_JOURNAL_MAX_BYTES env
Rotate the journal once it reaches this size, keeping one previous generation alongside it. Set 0 to never rotate.
HYPRUSE_JOURNAL_TEXT env
Set to 1 to record typed and copied text in the journal verbatim instead of as a length plus digest. Off by default because keystrokes are passwords; needed only to replay typing.
HYPRUSE_DRYRUN env
Set to 1 for a rehearsal: every acting tool validates its arguments and runs every trust guard, then reports what it would have done and delivers no input.

この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。

できること

パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。

基本チェックi

誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック

✓ 合格
作者とリポジトリが一致
レジストリ名は、リポジトリを所有するGitHubアカウント IlyasKhallouki で確認済みです
… 未チェック
今もメンテナンスされている
このリポジトリはまだGitHubから読み取っていません
… 未チェック
ライセンスがある
このリポジトリはまだGitHubから読み取っていません
– 対象外
エンドポイントが応答する
これはパソコンで動くため、インターネット上のエンドポイントはありません
– 対象外
OAuthでサインイン
パソコンで動き、代わりにローカルの設定を使います
… 未チェック
ツールの説明に隠れた指示がない
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです

その他のほかのサーバーとの比較i

このカテゴリのほかの32709件のうち0%よりスターが多い
このカテゴリのほかの32709件のうち66%より最近レジストリに公開
基本チェックの結果が、このカテゴリのほかの32709件のうち100%と同じかそれ以上

レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。

よくある質問

hypruseは安全ですか？

当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。

どんなキーやコードが必要ですか？

レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。

パソコンで動きますか、それともクラウドですか？

あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません（サーバー自体がオンラインサービスを呼び出す場合を除きます）。

今もメンテナンスされていますか？

GitHubリポジトリの最終更新は–、最新バージョン（0.13.0）がレジストリに届いたのは19 日前です。

どのアプリで使えますか？

Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。

代わりに使えるものは？

同じカテゴリには：Spec Driven Development, Remote Desktop Commander, SwarmMemo

代わりの候補

同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。

カードの見方：★ GitHubスターi3つの柱：レビュー · チェック · 利用状況i更新＝最新バージョンをレジストリに公開した日i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

パソコンで動く★ 440MIT14 か月前更新

インストール

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

クラウドで動く★ 211一昨日更新

インストール

SwarmMemo

作者：Hugo0

Talk with agent swarms: rooms, private messages and paid tasks for AI agents

クラウドで動く今日更新

インストール

作者のREADME

READMEを開く

作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。

hypruse

Computer use for [Hyprland](https://hypr.land). An MCP server that gives AI agents native hands on your Wayland desktop: workspaces, windows, mouse, keyboard, screenshots.

No ydotool daemon. No root. No portals. No X11.

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. desktop returns 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 through wtype'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.

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-hyprland does 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
`desktop`	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
`screenshot`	Focused monitor, one window by address (with grim 1.5+ on Hyprland 0.54+, even hidden or covered; metadata `visible` says whether the compositor draws it, `source` whether the pixels are the window's own or a screen crop, and a hidden capture may be stale), or `x,y,WxH` region; returns image + coordinate-mapping metadata; fast JPEG by default (`lossless=true` for PNG); `stable=true` waits for the frame to settle
`zoom`	Native-resolution re-capture around an estimated point (optionally clamped to a window): the precision step before clicking small controls, same metadata contract
`ui`	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
`marks`	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_ui`	Click a control by accessible NAME or by a `marks` number in one call: the coordinate comes from the tree. In the window you are in, the click goes through the real pointer (visible, same safety guarantees); in any other window, the control's accessibility action presses it in the background. An ambiguous name returns the candidates instead of guessing
`pointer`	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
`keyboard`	Type literal text (unicode-safe) or press app-level combos (`ctrl+shift+t`, `esc`, `F5`); an optional `window` address says where the keys go: the window you are in is focused and typed into, any other window gets them in the background. Compositor binds (`super+...`) go through `use_bind`, not here
`hypr`	Switch workspace, focus/move/close windows, fullscreen, floating (pure IPC, milliseconds; `close_window` also waits up to 1s for the destroy event, so its result and `then=` observation reflect the close instead of racing it)
`launch`	Start an app, silently on the next of the agent's own workspaces unless you name one (or pass `background=false` for yours), block on its actual `openwindow` event, return its address; detects single-instance apps (browsers) whose window ignores exec rules and moves it to the requested workspace
`binds`	The user's own keybinds, decoded (`SUPER+Q`, action, description); the agent runs one with `use_bind`
`use_bind`	Execute a keybind by combo (`SUPER+F`), running its bound action, so the agent drives the owner's own launchers and shortcuts. Not available for binds in a Lua `hyprland.lua`: those are anonymous closures Hyprland exposes no way to call, so `binds` shows them as action `lua` and `use_bind` says so instead of failing cryptically
`sequence`	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
`wait_for`	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 `already: true` instead of missing an event that fired before it subscribed. Replaces sleep-and-hope in multi-step automations
`clipboard`	Read or write the text clipboard via `wl-clipboard`; opt-in, exists only with `HYPRUSE_CLIPBOARD=1` in the server env

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

冒頭だけを表示しています。続きはリポジトリで読めます

hypruse

概要

PopNx MCPの3つの柱

できること

インストール

インストールの前に

自分で入力する値

できること

基本チェックi

作者とリポジトリが一致

今もメンテナンスされている

ライセンスがある

エンドポイントが応答する

OAuthでサインイン

ツールの説明に隠れた指示がない

その他のほかのサーバーとの比較i

よくある質問

代わりの候補

Spec Driven Development

Remote Desktop Commander

SwarmMemo

作者のREADME

hypruse

Why

How it works

Tools

Features

1. Semantic desktop control (start here)

2. Click controls by name, no pixels

3. Vision when it matters: the zoom loop