Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Agents use real GNOME/Wayland apps: on your screen, or an invisible second desktop you never see
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。
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。
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。
DESKWRIGHT_SESSION, DESKWRIGHT_INPUT_BACKEND必要なもの
どのアプリを使っていますか?
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": {
"deskwright": {
"command": "uvx",
"args": [
"deskwright"
],
"env": {
"DESKWRIGHT_SESSION": "your-value",
"DESKWRIGHT_INPUT_BACKEND": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add deskwright --env DESKWRIGHT_SESSION=your-value --env DESKWRIGHT_INPUT_BACKEND=your-value -- uvx deskwright動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"deskwright": {
"command": "uvx",
"args": [
"deskwright"
],
"env": {
"DESKWRIGHT_SESSION": "your-value",
"DESKWRIGHT_INPUT_BACKEND": "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。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"deskwright": {
"type": "stdio",
"command": "uvx",
"args": [
"deskwright"
],
"env": {
"DESKWRIGHT_SESSION": "your-value",
"DESKWRIGHT_INPUT_BACKEND": "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。
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。
DESKWRIGHT_SESSION envDESKWRIGHT_INPUT_BACKEND env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。
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。
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
レジストリ名は、リポジトリを所有するGitHubアカウント tristanmuzzu で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
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
パソコンで動き、代わりにローカルの設定を使います
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
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。
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。
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。
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)。
GitHubリポジトリの最終更新は–、最新バージョン(0.1.1)がレジストリに届いたのは2 か月前です。
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。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Draugr
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
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。
Computer use for AI agents on GNOME Wayland.
Let your coding agent use your Linux desktop. Or give it one of its own, so it stops stealing your mouse.
Install • What it can do • A desktop of its own • When something's off • Security
Claude Code can edit your files and run your commands. It can't open GIMP, click a button in a settings dialog, or read what a native app is showing you. On macOS and Windows it can, through computer use. On Linux that's still on Anthropic's list.
This fills the gap on GNOME. It's an MCP server plus a small shell extension, and it hands an agent the actual desktop: launching apps, reading widgets, clicking, typing, dragging, window management, OCR and screen recording. Any MCP client can drive it. Claude Code, Codex, Cursor, your own script.
The part people tend to like most: DESKWRIGHT_SESSION=headless runs all of it on a virtual monitor that isn't on any of your screens. Your agent gets a real GNOME desktop to work on, and it never takes your focus.
The beta adds guarded native controls, exact multi-control queries, adaptive visual fallback and shorter verified execution batches. It supports GNOME Wayland; Windows is not implemented. See the interaction guide and measurements and limits.
For a new installation:
pipx install --system-site-packages 'deskwright==0.2.0b1'
deskwright-setup
For an existing pipx installation, pipx upgrade --pip-args='--pre' deskwright keeps its existing system-site-packages setting. Run deskwright-setup to copy the updated extension, then log out and back in if setup reports a changed extension. Restart the MCP connection to load the updated Python tools. A connection restart alone cannot reload GNOME Shell's extension.
Wayland deliberately stops an application from seeing or touching any other window. That's a good rule, and it's why xdotool, wmctrl and grim either do nothing on GNOME or fail in ways that look like your own mistake. Every Linux computer-use project I found either shipped a Docker container running X11, or quietly assumed X11 and broke.
So I went looking for what GNOME actually permits, and it turns out to be quite a lot, just not where anyone looks. Mutter answers D-Bus. AT-SPI, the accessibility layer built for screen readers, exposes every real widget in every running app with its name, its role and the action it performs. And a shell extension runs inside gnome-shell itself, where the rest lives.
That middle one matters more than it sounds. Pressing a widget's own accessibility action isn't a nicer way to click. It's a different thing: it can't miss, it survives the window moving, and it needs no pointer at all. An agent working this way stops guessing at coordinates, and stops taking a screenshot after every action to find out what happened.
You need GNOME Shell on Wayland. Check with echo $XDG_CURRENT_DESKTOP $XDG_SESSION_TYPE, which should mention GNOME and wayland.
Open Claude Code, or Codex, or whatever you use, and say:
Set up https://github.com/tristanmuzzu/deskwright on this machine,
follow the AGENTS.md.
AGENTS.md is a runbook written for agents. Every command, how to check each one worked, the right package names for Debian, Fedora and Arch, and the handful of things that go wrong with their fixes. Your agent will ask you for a sudo password once and tell you to log out once. That's your whole involvement.
pipx install --system-site-packages deskwright
deskwright-setup
deskwright-setup narrates every step. It turns on the accessibility flag, installs the bundled shell extension, and tells you about any missing system package with the right install line for your distro, so you're never guessing at package names. It never runs sudo itself.
Then log out and log back in. Once. There's no way around this one: on Wayland, gnome-shell only picks up an extension at session start.
Last step, point your client at it:
claude mcp add deskwright --scope user -- deskwright
That's it. Ask your agent to open an app and it will.
Why --system-site-packages , and what breaks without it
PyGObject publishes no wheels to PyPI. It's a distro package everywhere (python3-gi, python3-gobject, python-gobject), so an isolated venv can't import it. Leave the flag off and you get a server that starts cleanly and then dies on the first click with input_backend_failed.
uvx has no equivalent flag, which is the only reason this says pipx. If you'd rather skip pipx, a plain python3 -m venv --system-site-packages followed by pip install deskwright works identically.
As a Claude Code plugin instead
The repo is also a plugin marketplace. It registers the server plus a skill that teaches an agent which tool to reach for first.
claude plugin marketplace add tristanmuzzu/deskwright
claude plugin install deskwright@deskwright
The plugin runs the server from its own checkout, so there's no pip install. You still need the system packages and the extension, so run the setup out of the checkout Claude Code cloned for you, once:
~/.claude/plugins/marketplaces/deskwright/bin/deskwright-setup
Then log out and back in, same as above.
From a clone, if you want to hack on it
git clone https://github.com/tristanmuzzu/deskwright
cd deskwright bin/deskwright-setup ./mcp_server.py --self-test
./mcp_server.py is the same entry point as the deskwright command, by the path older registrations already point at. CONTRIBUTING.md has the layout and which test suites need a real session.
DESKWRIGHT_SESSION=headless deskwright --self-test
You want 18/18 passed. It runs on a virtual monitor rather than your screen, so it's safe to run while you're working. The first run takes about 20 seconds because it has to start a second gnome-shell.
Drop DESKWRIGHT_SESSION=headless and it tests your real desktop instead. Do that one while you're looking at the screen: the self-test injects real input, because it's checking the guards that refuse dangerous key combinations.
When something's wrong, ask your agent to call desktop_health. It answers in one line whether this desktop is usable, then says which mechanisms work right now and what each of them will actually do.
41 tools. Each returns enough that you do not need a second call to work out what happened. The order below is the order an agent should reach for them. Use native controls and exact queries where useful, with screenshots and ordinary input for visual work or incomplete accessibility.
| Tool | What it's for |
|---|---|
ui_apps, ui_tree, ui_find | Find things. ui_find searches 30 levels deep by default, because GTK4 nests far deeper than you'd expect. |
ui_press | Compatibility API for invoking a widget by index path. Requires expect_name or expect_role; inspect the resulting state. Prefer ui_action for native identity and modal guards. |
ui_observe, ui_snapshot, ui_query, ui_inspect, ui_action, ui_wait | Bounded native references, guarded actions and exact completion checks. See semantic interaction. |
ui_set_text | Compatibility API for writing by index path, with exact readback. Prefer ui_action for native references, current-value comparison and modal guards. |
ui_read_text | Read a widget's contents. This is how you verify something worked. |
launch_app | Start an app by desktop id and wait for its window, inside one call. |
screen_map | Where everything is, in pixels: windows top of stack first, plus every pressable widget of the focused app with the point to click it at. Each carries a ref: N you pass straight to ui_press or pointer_click. No coordinates to copy, identity re-checked on use. |
pointer_click, pointer_move, pointer_drag, pointer_scroll | Real pointer input in absolute screen coordinates. Pass expect_window and a click that would land somewhere else is refused, with the blocker named so you can redirect in the same call. |
pointer_path | Draw a continuous curve through a list of screen points, with one button press, bounded duration and interruption checks. Requires a target window. |
window_at, pointer_position | What a click at a point would hit, before you click it. And where the pointer is now, or an honest note that only the last position it set is known. |
find_text | Where a visible string is, in screen coordinates. OCR, about 0.3s for a window, and no image in your transcript. This is the answer for Chrome, Electron and Qt, which expose almost nothing to ui_find. |
wait_for | Wait for a window, a widget, some text, a focus change or the clipboard, instead of sleeping a guessed number of seconds. |
region_changed | Wait for pixels to change. For what wait_for can't express, like a reply arriving or a spinner stopping. |
assert_state | Pass or fail with evidence, so a long run can decide for itself that it's finished. |
do_steps | A known sequence in one call, validated before anything runs, with per-step retry and one picture at the end, or at the step that broke. |
list_windows, activate_window, window_layout, window_manage | Window list, focus and layout. window_layout cannot close windows; general window_manage retains close. |
screenshot, zoom | A picture, or a full-resolution crop of one window, region or widget. zoom never scales, so small text stays readable. |
screencast, frames | For anything that moves, because a still can't show motion. frames also reports a per-frame delta series, which is how you tell a smooth scroll from a juddering one. |
type_text, press_keys, hold_key | Keyboard input through compositor keysyms, with focus proven before anything gets typed. |
clipboard_read, clipboard_write | Pasting beats two thousand keystrokes, and reading back is how you check it arrived. |
journal | The trail of everything the agent did: arguments, outcome, whether it landed, screenshot hashes. For reviewing an unattended run, or working out where you are after a context reset. |
desktop_health | One line on whether this desktop is usable, then the detail. |
An agent that needs your screen is only half useful. deskwright-headless starts a separate GNOME session on a virtual monitor, with its own session bus, its own gnome-shell --headless and its own runtime directory. A server pinned to it drives that desktop with the same 41 tools while you keep the physical one.
deskwright-headless start # about 200 MB of gnome-shell, idempotent
deskwright-headless status # live
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