Glovebox MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 2 Nov 2026.
Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
What the code does
We read the source, 23 h ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
xeph = subprocess.Popen(
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
return subprocess.run(["xdpyinfo", "-display", _disp(n)], capture_output=True,
return os.path.join(TMP, f"app_{int(n)}.log")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
A tool parameter here reaches a dangerous call
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Alternatives to Glovebox MCP
same job, measured the same wayPersistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.
Verified desktop control for agents on Windows and Linux: apps with no API, windows, shell, browser.
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents
Self-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent.
Windows screenshots, OCR, and redacted screen recording for AI agents. No desktop app needed.
Real Chromium browser for AI agents: compact outlines, diff-only replies, real input, you approve.
Open automation engine for AI agents. Control live browsers and desktop apps locally.
Background Windows desktop for AI agents: native GUI automation, screenshots and app testing.
Glovebox MCP — questions
Answers built from our own checks of this server.