Unterm runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 1 Nov 2026.
The terminal AI agents can drive: spawn panes, run commands, read screens, scrolling screenshots.
What the code does
We read the source, 23 h ago · rules 995398eba69f
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.
if ( IsDebuggerPresent() )
subprocess.check_call(cmds)
while (curr + drop < max) {
left -= count[curr + drop];
dictionary.add(agl_glyphs[g], eval("0x" + agl_values[g]))
abs_path = os.path.join(base_srcdir, s)
if let Ok(rc) = std::fs::read_to_string(home.join(".npmrc")) {
m.innerHTML = state.inbox.map(item => {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Unterm
same job, measured the same wayLets AI agents drive a real terminal: type, press keys, click, read the screen, take screenshots.
Drive the browsers of running ZennoPoster tasks: open pages, read and click elements, screenshots.
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
Drive the browser of ZennoPoster ProjectMaker: open pages, read and click elements, screenshots.
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
UI design from prompts, screenshots, and URLs for AI coding agents and theme tokens.
Unterm — questions
Answers built from our own checks of this server.