Glovebox MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 7 Jul 2026.
Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
We read the source, 21 h ago · rules 3dff92dd89df
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).returncode == 0
prof = os.path.join(HERE, "profiles", f"chromium-{n}")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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.
Browser-native AI agents for X (Twitter): multi-account, MCP-ready, no X API key required.
Real signed-browser automation for AI agents, over a local stdio MCP server.
Headless browser primitives for AI agents when sites need real JS rendering.
Native macOS browser exposing an MCP server so AI agents can drive a real WKWebView.
Desktop UI automation for AI agents: screenshots, windows, mouse, keyboard, UI Automation, OCR
Answers built from our own checks of this server.