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.
This commit is contained in:
parent
5906cc2f2b
commit
0b3268feae
8 changed files with 311 additions and 1 deletions
|
|
@ -8,6 +8,7 @@ members = [
|
|||
"hive-bash-mcp",
|
||||
"hive-c0re",
|
||||
"hive-claude",
|
||||
"hive-screen-mcp",
|
||||
"hive-forge",
|
||||
"hive-host-sock",
|
||||
"hive-jobq",
|
||||
|
|
|
|||
Loading…
Reference in a new issue