About io.github.segentic-lab/glovebox-mcp
io.github.segentic-lab/glovebox-mcp is an MCP server in the Browser category: sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows.
Install
git clone https://github.com/segentic-lab/glovebox-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
click_element(id)Click an element from the last `parse_screen` (no coordinate guessing).
Parameters not published.
list_files()The instance's staging folder `files/<N>/` (under the install dir) + its contents.
Parameters not published.
open_file(filepath, app?)Open a local file in a **native** app on the instance's display (e.g. `app="gimp"`) or via `xdg-open`. GTK apps get the same X11/D-Bus handling as `launch_app`.
Parameters not published.
parse_screen()Vision grounding → JSON of detected elements (id, type, label, interactive, pixel-center; capped at 300 per call, flagged via `"truncated"`) + a numbered Set-of-Mark image at `/tmp/glovebox_annotated_<N>.png`. (`local` mode: OmniParser on GPU, ~2 s.)
Parameters not published.
press_keys("ctrl+a"/"Return"/…)Keys/combos (xdotool syntax).
Parameters not published.
screenshot()Screenshot of an instance.
Parameters not published.
status()Server + sandbox status in one read-only call: version, vision backend, host display, live instances, and which system deps (xdotool, xclip, Xephyr, tesseract, OmniParser weights) are present. Run it first — and paste it into bug reports.
Parameters not published.
type_text(text)**Unicode-safe** typing (ASCII via xdotool; anything with č/š/ž… is inserted via the clipboard, because xdotool's synthetic unicode is silently dropped by some GTK apps).
Parameters not published.
upload_file(filepath, selector?)Attach a local file to a page's `<input type=file>` via the **Chrome DevTools Protocol**. The nested X11 file picker is invisible to automation **and hangs the renderer**, so use this for all uploads — never click an upload button expecting a dialog. Works on Chromium started by `launch_app`/`start-display.sh` (they open a per-instance `--remote-debugging-port`, `9222+N`). **Browser file inputs only** — for native apps see `open_file`.
Parameters not published.
Ask AI
Ask AI about io.github.segentic-lab/glovebox-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.