Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SIDEHAND_ALLOWNoLimits which windows Sidehand can see (text read from other windows is passed to your agent, so this restricts the set of allowed windows).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

sidehand reads and operates Windows desktop apps in the background while the user keeps working. Read a window with ui_tree (compact text, a ref per control), act on refs with ui_act, use ui_wait instead of sleeping. Prefer ui_tree over capture: it costs a few hundred tokens instead of an image. If ui_tree shows almost nothing (games, custom-drawn apps), ui_ocr reads the text with clickable refs. Never take the user's focus: pass allow_foreground or bring_to_front only after the user agreed. If a result ends with WARNING (the app came forward anyway), tell the user and do not repeat that action while they are busy.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_windowsA

List visible top-level windows (handle, size, title).

list_monitorsB

List monitors with their virtual-desktop coordinates.

ui_treeA

A window's controls as compact text, one line per control with a ref (e12). Long lists show 25 items; filter prints matching lines only (refs still cover the window); rects adds screen rectangles. If it shows almost nothing (games, Qt, canvas apps), use ui_ocr.

ui_ocrA

Only when ui_tree shows almost nothing (games, Qt, Sciter, canvas UIs): the window's text read by Windows OCR, one line per text with a ref (t3) and screen rect. ui_act takes a t-ref for click, double-click, right-click, hover, wheel and drag, posted at the text's center as mouse messages (no real cursor, no focus change). About 0.5 to 2 s; works while covered. t-refs expire after 60 s.

ui_waitA

Poll a window until a control containing text appears (or, with gone, disappears). Use instead of sleeping.

ui_actA

Act on a ref from the latest ui_tree/ui_wait/ui_ocr without moving the mouse or the user's focus. click | type (replace text) | check | uncheck | select (value= inside a list/combo) | expand | collapse | scroll | right-click | double-click | hover | wheel (value 'down 3') | drag (value= or 'dx,dy') | press (value 'Enter', 'ctrl+a', 'Down Down Enter'). press works in the background on classic controls and on a visible text field of a browser or Electron window. focus, and press on other WPF/browser controls (except Enter on a button or link), take the user's foreground: only with allow_foreground after the user agreed; press hands the foreground back once the keys are in, focus keeps it. If an action fails, never fall back to moving the real mouse or bringing the window forward yourself; tell the user. Refs expire when a window is read again.

windowA

Move ('x,y'), resize ('w,h'), minimize, restore (back behind the user's windows) or close a window without activating it.

launchA

Start an app, document or URL without it taking the user's focus.

clipboardA

Read the clipboard text, or replace it with text (that overwrites what the user copied; prefer ui_act type).

captureA

Screenshot: full, monitor, region, active or window (PrintWindow, works while covered). Returns the image. Capturing a minimized window restores it, so it needs bring_to_front after the user agreed.

cropB

Crop a PNG to a rectangle in image pixels. Returns the image.

maskB

Hide private information in a PNG before sharing it: black, pixelate or blur rectangles. Returns the image.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct resource or action: image ops (capture/crop/mask), enumeration (list_windows/list_monitors), UI inspection (ui_tree/ui_ocr), and interaction (ui_act/ui_wait/window/launch). The ui_tree vs ui_ocr boundary is explicitly defined, and ui_act vs window is clearly separated (control-level vs window-level manipulation). The remaining overlap (capture/crop/mask) is a natural pipeline where each step is unambiguous.

Naming Consistency4/5

All names are lowercase snake_case with predictable families: list_* for enumeration, ui_* for UI automation, and bare verbs for image/clipboard actions. Minor inconsistency in that some tools are bare nouns (clipboard, window) while siblings are verbs (capture, crop, launch), but the grouping remains readable and predictable.

Tool Count5/5

Twelve tools is well within the ideal band and each one covers a needed capability of desktop automation (capture, inspect, act, window control, launch). No tool appears redundant or vestigial, and the surface is not bloated.

Completeness4/5

The lifecycle is broadly covered: discover windows/monitors, inspect via UI tree or OCR, act, wait, and manage window state. Gaps are minor: clipboard is text-only, there is no explicit window-activate tool (handled indirectly via ui_act focus), and no process-level launch/terminate or wait-for-window-primitive beyond ui_wait on controls.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues