hush
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Hush drives desktop apps in the background. observe an app to get refs, then act with several steps per call; each act answers with what changed, so observe again only when you need parts you haven't seen.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| appsA | List running apps, or find running and installed apps by name. |
| observeA | Outline of an app's window: one line per element, each with a ref like b3 or t1 for act. Later calls return only what changed. Long parts are folded; pass focus to open one. In apps that draw their own interface, labels read from the pixels appear as |
| actA | Run steps on an app's window in the background, without touching the user's focus, pointer or clipboard. Steps run in order, each waits until the app has finished reacting, and the batch stops at the first failure. Returns what changed. Put several steps in one call. Steps: click REF|X,Y · double REF · right REF · set REF VALUE · type [REF] TEXT · key COMBO [xN] · menu A > B · pick REF OPTION · select REF · focus REF · scroll REF up|down|left|right [N] · show REF · drag REF|X,Y to REF|X,Y (to a ref: takes its place) · wait gone REF|REF|text "T"|500ms [within 10s] · lane (move the app's windows off screen, where they still render and take clicks) |
| timelineA | Play key and pointer events on a millisecond schedule in an app's window, in the background. For input whose timing matters: music, games, drags, holds. Plan the whole sequence, then send it once. One event per line, MS VERB ARGS (MS = time from the start): MS down KEY · MS up KEY · MS tap KEY [HOLD_MS] · MS down X,Y [right] · MS up X,Y [right] · MS move X,Y · MS tap X,Y [HOLD_MS] [right]. KEY like a, shift+a, space, left. X,Y are window points. HOLD_MS defaults to 40. |
| scriptC | Run AppleScript (default) or JavaScript for Automation. Best for apps with a scripting dictionary. Returns the result as text. |
| seeA | Screenshot of a window, or of one element by ref. Only for what the outline can't show: canvases, video, images, charts. |
| recordA | Record a window to MP4 for a demo: start, act, then call with stop. The video shows an animated cursor at each action, in real time. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The tools mostly target distinct phases of GUI automation: listing apps, observing structure, acting, timed input, scripting, screenshots, and recording. observe vs see and act vs timeline overlap somewhat, but the descriptions draw clear boundaries. An agent should usually select the right tool without serious confusion.
All names are short lowercase single words, which is stylistically consistent. However, the set mixes verbs (observe, act, see, record) with nouns (apps, timeline, script), so there is no predictable action-oriented naming pattern. It remains readable, but boundaries rely on descriptions rather than names.
Seven tools is well-scoped for a macOS GUI automation server. Each tool has a clear role, and none feels redundant or extraneous. The surface is neither thin nor bloated.
The set covers the core automation loop: find apps, observe UI structure, act, send timed input, script, take screenshots, and record demonstrations. Minor gaps exist, such as no explicit app launch/quit/window-management tool, but scripting can likely fill those gaps. Overall the surface is robust with only small workaround-level omissions.