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
13
Cargo.lock
generated
13
Cargo.lock
generated
|
|
@ -1734,6 +1734,19 @@ dependencies = [
|
|||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hive-screen-mcp"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"rmcp",
|
||||
"schemars",
|
||||
"serde",
|
||||
"tokio",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hive-sh4re"
|
||||
version = "0.1.0"
|
||||
|
|
|
|||
Loading…
Reference in a new issue