I Got Tired of Alt-Tabbing to a Real Terminal, So I Built My AI a Front Door

Developer Rehan30g built Conduit, a Python-based approval tool that lets AI coding agents request permission to run system commands via a popup dialog, eliminating the need to alt-tab to a terminal. The tool binds to localhost, uses session tokens, and defaults to denying requests, with support for MCP and plain HTTP.

So you're deep in a session with Claude Code or Cursor, everything's flowing, and then it hits a wall: "I can't install this package system-wide, I don't have sudo." And you're sitting right there, hands on the keyboard, perfectly willing to run that one command yourself. But instead you have to stop, alt-tab to a real terminal, type it out, come back, and re-explain what just happened so the agent can pick up where it left off. Every time. All day. The sandbox isn't wrong, by the way. You want your AI boxed in — nobody wants an agent that can quietly touch /etc or fiddle with firewall rules on its own initiative. The problem isn't that the sandbox exists. It's that there's no door in it. No way to say "yes, this one, go ahead" without leaving the conversation entirely. That's the whole reason I built Conduit . Conduit is a small Python process that runs on your machine, with whatever privileges you give it. Your AI proposes a command. You get a popup showing exactly what it wants to run. You click Yes or No — and it defaults to No, on purpose. Nothing executes without you personally reading it first. Starting it is about as complicated as it gets: python run conduit.py That's it. No pip installs, standard library only. It opens a local dashboard, prints a session token, and waits. conduit.bat on Windows . DENIED and that's the end of it.No silent execution, no "trust me," no background magic. If your client speaks MCP Claude Code, Cursor, Claude Desktop , this is genuinely one command: claude mcp add conduit -- python /full/path/to/run conduit.py --mcp That gives the agent a native run command tool, plus read-only list shells and get status that don't need your approval at all. Worth noting: the MCP piece is just a thin bridge. It runs inside the agent's own sandbox and can't execute anything itself — it just forwards the request over localhost to the real Conduit process, which is the one actually holding the keys and the dialog box. If MCP isn't an option, plain HTTP works too, and it's about eight lines of stdlib Python: python import urllib.request, json req = urllib.request.Request "http://127.0.0.1:40404/", data=json.dumps {"command": "brew install ffmpeg"} .encode , headers={"Authorization": "Bearer YOUR TOKEN"}, method="POST" print json.loads urllib.request.urlopen req .read Both paths land in the same queue and the same approval dialog. Doesn't matter which one your tool prefers. The security details matter more than the UI here, so a quick rundown: it binds only to 127.0.0.1 , never touches your network. Every session gets a fresh UUID token that dies when you close Conduit — nothing persists, no history lingers around waiting to be a problem. Unanswered prompts auto-deny after 60 seconds instead of hanging open forever. And there's a --headless flag with --always-allow baked in for when you're running on a VPS and genuinely trust the pipeline — but that's opt-in, never the default. Mostly it's the small stuff that used to break my flow: apt install -ing a missing system dependency, restarting a local service after a config change, checking disk space, tweaking something in a protected directory. None of it is dangerous when you're the one clicking approve. It was only ever annoying because there was no clean way to approve it without leaving the chat. Conduit doesn't make your AI more powerful. It just gives you a button. Repo's here if you want to poke at it: github.com/Rehan30g/Conduit https://github.com/Rehan30g/Conduit