umbriel-mcp

mcp-name: io.github.dot-ASH/umbriel-mcp

An MCP server for the Umbriel Wayland compositor.

Exposes Umbriel to MCP clients: list and control windows, workspaces and outputs, drive the pointer and keyboard, capture the screen with optional OCR, and read or write the clipboard.

Compositor state and actions go straight to Umbriel's IPC socket rather than shelling out to the CLI, so inspection costs one round trip and no process spawn. Pointer, keyboard, and clipboard use Wayland protocols directly. Only screen capture and OCR call external programs.

Read this before installing

Full access means full control of your desktop. In the default full profile an agent connected to this server can launch arbitrary commands, type and click anywhere, read and overwrite your clipboard, and see your screen. Anything on screen or in the clipboard is visible to the model. Use the profiles to grant less.

This is a best-effort personal project that tracks an actively evolving compositor. Expect 0.x behavior changes, and expect it to break when Umbriel changes. There is no support promise beyond what I can do in my spare time.

Related MCP server: claude-workman

Compatibility

Support follows Umbriel's own availability: if Umbriel runs on your system, this server should. The server itself is a static binary for x86_64 and aarch64 Linux with no runtime libraries, so the distribution only matters for installing Umbriel and the two screen helpers.

Older Ubuntu releases are not supported because Umbriel is not packaged for them.

Warning for Arch users: the AUR package named umbriel is a placeholder and is not the compositor. Do not install it; the compositor is umbriel-git.

Install

Each path below installs Umbriel, the screen helpers, and umbriel-mcp, then checks the result. Skip the Umbriel step if you already run it. The Umbriel commands are copied from its installation page; check there if they have changed.

Arch Linux

yay -S umbriel-git                                     # the compositor, if needed
sudo pacman -S grim tesseract tesseract-data-eng       # screen capture and OCR

Then install the server as a pacman package built from this repository's recipe. It downloads the prebuilt release binary and checks its checksum, so nothing is compiled:

git clone https://github.com/dot-ASH/umbriel-mcp
cd umbriel-mcp/packaging/aur-bin
makepkg -si
umbriel-mcp doctor

Remove it later with sudo pacman -R umbriel-mcp-bin. An AUR package of the same name is planned; this section will switch to yay -S umbriel-mcp-bin once it is published.

Ubuntu 26.04 and newer

1. Install Umbriel from the Noctalia APT repository (amd64 and arm64 only), if needed:

   wget https://pkg.noctalia.dev/deb/nickh-archive-keyring.deb
   sudo dpkg -i nickh-archive-keyring.deb
   sudo wget -O /etc/apt/sources.list.d/noctalia-resolute.sources \
     https://pkg.noctalia.dev/deb/noctalia-resolute.sources
   sudo apt update
   sudo apt install umbriel

2. Install the screen helpers:

   sudo apt install grim tesseract-ocr tesseract-ocr-eng

3. Install the server from the latest GitHub release:

   arch=$(uname -m)   # x86_64 or aarch64
   tag=v0.2.1
   base="https://github.com/dot-ASH/umbriel-mcp/releases/download/$tag"
   curl -LO "$base/umbriel-mcp-$tag-$arch-linux.tar.gz"
   curl -LO "$base/SHA256SUMS"
   sha256sum --check --ignore-missing SHA256SUMS
   tar -xzf "umbriel-mcp-$tag-$arch-linux.tar.gz"
   sudo install -Dm755 "umbriel-mcp-$tag-$arch-linux/umbriel-mcp" /usr/local/bin/umbriel-mcp

   /usr/local/bin is on every user's PATH, so harnesses started from the Umbriel session find the binary without extra setup. To install without sudo, use ~/.local/bin/umbriel-mcp instead; Ubuntu adds ~/.local/bin to PATH at login only if the directory already existed, so log out and back in after creating it.

4. Check the setup from a terminal inside the Umbriel session:

   umbriel-mcp doctor

Debian Trixie and Sid

Same as Ubuntu, with the Debian repository source and, on Trixie, the backports suite:

wget https://pkg.noctalia.dev/deb/nickh-archive-keyring.deb
sudo dpkg -i nickh-archive-keyring.deb
sudo wget -O /etc/apt/sources.list.d/noctalia-trixie.sources \
  https://pkg.noctalia.dev/deb/noctalia-trixie.sources        # Sid: noctalia-unstable.sources
sudo apt update
sudo apt install -t trixie-backports umbriel                  # Sid: sudo apt install umbriel
sudo apt install grim tesseract-ocr tesseract-ocr-eng

Then install the server from the release binary as in step 3 above and run umbriel-mcp doctor.

Fedora

sudo dnf install umbriel-nightly                              # from the Terra repository
sudo dnf install grim tesseract tesseract-langpack-eng

Then install the server from the release binary as in Ubuntu step 3 and run umbriel-mcp doctor.

Other distributions

Install Umbriel following its installation page, then grim, tesseract, and Tesseract's English data (eng.traineddata) from your package manager. Install the server from the release binary as in Ubuntu step 3, or build it with Cargo (needs Rust 1.89 or newer, for example from rustup):

cargo install umbriel-mcp --locked

umbriel-mcp doctor names the exact packages to install on Arch, Debian/Ubuntu, and Fedora, and gives generic guidance elsewhere.

Requirements

Pointer, keyboard, and clipboard need nothing beyond a running Umbriel session. These external programs are needed only for the screen tools:

The tools are always listed; a call that needs a missing program fails with an error naming the package to install.

The socket is found through UMBRIEL_SOCKET, falling back to $XDG_RUNTIME_DIR/umbriel-$WAYLAND_DISPLAY.sock.

Register with your harness

umbriel-mcp install pi            # also: claude-code, vscode
umbriel-mcp install opencode      # also: cursor, zed (prints config to paste)
umbriel-mcp install claude-code --profile no-exec

For pi, claude-code, and vscode this runs the harness's own CLI (pi mcp add, claude mcp add, code --add-mcp). For opencode, cursor, and zed it prints the configuration to paste; it never reads or edits your config files. A profile is added to the registration only if you pass --profile, so the default stays full. The pi registration uses direct exposure and a description, so the model sees the tools in its tool list and answers "what's on workspace 4?" with one list_windows call instead of searching for tools or trying hyprctl. If you registered by hand earlier, run umbriel-mcp install pi again to switch to direct exposure. The Zed snippet keeps "args": [] because Zed rejects its whole settings file if it is missing.

Any other MCP client can use the plain stdio form:

{
  "mcpServers": {
    "umbriel": { "command": "umbriel-mcp", "args": [] }
  }
}

Checking your setup

umbriel-mcp doctor verifies that the Umbriel socket is reachable, that the compositor offers the virtual-pointer and virtual-keyboard protocols, and that grim, tesseract, and Tesseract's English data are installed. Each problem is listed on its own with the command to fix it on Arch, Debian/Ubuntu, and Fedora, or generic advice on other distributions. It exits with status 0 only when everything is ready.

Profiles

--profile limits what the server will do. Every tool stays visible in every profile; a call the profile does not allow returns an error that names the profile.

no-exec stops the server from starting programs; it is not a sandbox. An agent that can type into a focused terminal can still run commands through the input tools.

Tools

Inspection — list_windows, list_workspaces, list_outputs, get_active_window, list_layers

Window and workspace control — switch_workspace, focus_window, close_window, kill_window, move_window_to_workspace, toggle_fullscreen, toggle_floating, resize_window, set_workspace_layout, toggle_overview, launch_app, run_action

Input — mouse_move, mouse_click, mouse_scroll, mouse_drag, type_text, key_press

About Umbriel itself — umbriel_info (version, keyboard layouts, submap, color and tearing state), list_actions (every action run_action and keybinds accept, filterable), config_options (exact config keys with types, defaults and allowed values, from Umbriel's own schema), read_config (your config or one section such as keybinds, plus validation). These read from the installed umbriel command and your config, so they match the version you run. The schema has no prose descriptions; explanations live in the Umbriel documentation.

Changing keybinds — set_keybind and remove_keybind edit the [keybinds] table of your ~/.config/umbriel/config.toml. Each edit is checked with umbriel config validate before the file is replaced, so a rejected action or chord never goes live. The previous config is saved next to it as config.toml.bak-<time>, only the changed line differs (comments and formatting are kept), a symlinked config stays a symlink, and a chord bound in an [include] file is left alone. Umbriel applies the change immediately. read-only refuses edits, and no-exec refuses any binding to a spawn: action, because a keybind that starts a program would let an agent run commands later through you. Backups are not cleaned up automatically.

Screen and clipboard — screenshot, screenshot_with_ocr, find_text_on_screen, click_text, clipboard_read, clipboard_write. With a window_id, screenshot and screenshot_with_ocr capture that window even on a hidden workspace, without switching to it (needs grim 1.5 or newer; older grim can only capture windows that are on screen).

key_press takes chords such as ctrl+shift+Tab, super+q, F5 or alt+Left; an uppercase letter (ctrl+A) implies Shift. type_text accepts any Unicode text, with \n typed as Return and \t as Tab.

run_action accepts any action from umbriel msg --help, so the compositor's full verb set stays reachable even where there is no dedicated tool.

Notes

Workspaces in Umbriel belong to an output rather than to a global pool. Selectors take a position or a name and accept an optional /output suffix, which the workspace and output arguments build for you.

Screenshots are downscaled to 1024px wide by default and returned as JPEG alongside a coordinate-mapping note, so screen coordinates can be recovered from image coordinates. OCR is different: it always runs on the full-resolution capture, because recognising text in the downscaled preview finds nothing. find_text_on_screen and click_text therefore report absolute screen coordinates directly, and match multi-word phrases such as Open File.

License

MIT