Commit graph hyperhive/hive-screen-mcp
Author SHA1 Message Date
iris
7fa7e2bdfd refactor(#2305): drop mouse tools + ydotool, switch key_press to wtype
- 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).
2026-07-20 20:55:27 +02:00
iris
584dfed0c9 fix(#2305): run_cmd returns Result, nix fmt, collapse nested if
- run_cmd now returns Result<String, String> — callers pattern-match
  instead of comparing against an "ok" sentinel string
- Add cmd_result() helper to format run_cmd results as tool strings
- mouse_click: collapse nested if-let into let-chain (clippy collapsible_if)
- nix fmt: reformat screen.nix package list
2026-07-20 20:55:27 +02:00
iris
0b3268feae feat(#2305): hive-screen-mcp — screenshot + input MCP for GUI agents
New crate hive-screen-mcp: a stdio MCP bridge activated automatically
when an agent has hyperhive.gui.enable = true. Provides five tools:

- screenshot   — grim → saves PNG, returns path for Read tool
- type_text    — wtype → Unicode text input (no daemon)
- key_press    — ydotool key → combos like ctrl+c, super+l
- mouse_move   — ydotool mousemove --absolute
- mouse_click  — ydotool click, optionally with prior move

New nix/agent-modules/screen.nix: wires the MCP bridge into
extraMcpServers.screen; adds grim + wtype to systemPackages. Adds
hyperhive.gui.screenInput option (default false) which enables the
ydotoold daemon + ydotool for mouse/keyboard injection via /dev/uinput.

screenshot and type_text work without screenInput. key_press,
mouse_move, and mouse_click return a ydotool error until ydotoold is
running and /dev/uinput is accessible in the container.
2026-07-20 20:55:27 +02:00