perch
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COMPUTER_USE_LINUX_HYPRLAND_BACKGROUND | No | Hyprland: keys and window screenshots without focusing the window. `0` turns it off. | 1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_windowsA | Open windows, one per line: id, app, title, focused, workspace. |
| read_windowA | A window's buttons, fields and text as compact lines, e.g. [e34 button "Save" disabled]. Act on them with act_window using the e-refs; a new read_window (of any window) replaces them. |
| read_screenshotA | Picture of one window (or the whole screen without window), longest side max_edge px. A window is captured in the background on Hyprland; elsewhere it comes to the front. Costs image tokens: prefer read_window. With file, saves a PNG there instead. |
| read_statusA | Whether desktop control works here: accessibility, input, windows, and what blocks it. |
| act_windowA | Run steps in one window, in order, stopping at the first that fails: click, type, key, set, action, scroll, drag, focus, wait. Targets are e-refs from read_window or [x, y] pixels of its read_screenshot; drag takes pixels of a whole-screen read_screenshot. Element clicks, set and action never bring the window to the front; keys and typing don't on Hyprland, elsewhere they focus it. Mouse steps ([x, y] clicks, right or double clicks, scroll, drag) need a focus step first, which shows the window to the user. focused: true sends keys to the focused window, refused if the focus moved. then: tree (default after read_window) or screenshot (brings the window forward except on Hyprland) shows the result. |
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 5 tools
read_window (element tree of one window) vs read_screenshot (image) is cleanly separated, and act_window is clearly the write-side counterpoint. The only real risk is read_window vs read_windows, where the plural name could be misread as 'read contents of all windows' rather than 'list open windows', though the description disambiguates.
All names are snake_case verb_noun (read_window, read_windows, read_screenshot, read_status, act_window), with a natural read/act split that maps to inspect vs. manipulate. No mixed conventions or vague verbs like process/run.
Five tools is tight and well-scoped: four read-side probes (element tree, window list, screenshot, capability status) plus one consolidated act_window that absorbs click/type/key/scroll/drag/focus/wait as steps. Nothing feels redundant or absent on count grounds.
The lifecycle of inspect-then-act on existing windows is fully covered, including a preflight read_status and post-action 'then' verification. Gaps remain around launching apps/closing windows and clipboard access, so an agent can inspect and drive open windows but cannot start a program itself.