7fa7e2bdfd
- remove mouse_move and mouse_click (no Wayland-native alternative on Weston without /dev/uinput; follow-up filed for future investigation) - replace key_press from 'ydotool key' to 'wtype -k': parses mod1+mod2+key into -M mod1 ... -k key ... -m mod1 sequence via virtual-keyboard protocol - remove dest_path parameter from screenshot: always writes to /tmp/ (fixes arbitrary write-path concern from security review) - simplify screen.nix: drop screenInput option, ydotoold systemd unit, ydotool package; only grim + wtype remain (both compositor-mediated, no /dev/uinput) - update module header comment to reflect three-tool surface Addresses mara's /dev/uinput veto (PR #2617 comment #40524).
32 lines
1 KiB
Nix
32 lines
1 KiB
Nix
# Screen MCP — screenshot + keyboard input for GUI agents.
|
|
#
|
|
# Auto-activated when `hyperhive.gui.enable = true`. Wires the
|
|
# `hive-screen-mcp` stdio bridge as `extraMcpServers.screen` so claude
|
|
# gets three tools: `screenshot`, `type_text`, and `key_press`.
|
|
#
|
|
# All tools use Wayland protocols mediated by the Weston compositor —
|
|
# no `/dev/uinput` or kernel-level injection needed. `grim` takes
|
|
# screenshots; `wtype` handles both text input and key/modifier combos
|
|
# via the `zwp-virtual-keyboard-unstable-v1` protocol.
|
|
{
|
|
pkgs,
|
|
lib,
|
|
config,
|
|
...
|
|
}:
|
|
{
|
|
config = lib.mkIf config.hyperhive.gui.enable {
|
|
# Register the screen MCP bridge so claude gets the screen tools.
|
|
hyperhive.extraMcpServers.screen = {
|
|
command = "${config.hyperhive.packages.hive-screen-mcp}/bin/hive-screen-mcp";
|
|
args = [ ];
|
|
};
|
|
|
|
# grim: Wayland screenshot; wtype: text + key input via virtual-keyboard
|
|
# protocol (compositor-mediated, no /dev/uinput required).
|
|
environment.systemPackages = [
|
|
pkgs.grim
|
|
pkgs.wtype
|
|
];
|
|
};
|
|
}
|