XuLan ScreenPilot runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 6 Nov 2026.
Turn the real Windows screen into a numbered element table your AI agent can operate.
What the code does
We read the source, 20 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.
r = subprocess.run([sys.executable, os.path.join(BASE, "screenpilot.py"), *参数],
return io.open(os.path.join(根, p), encoding='utf-8').read()
for (var i=0;i<40;i++){document.write("<p style='margin:34px'>段落第"+i+"行 滚动单步靶文本"+i+"</p>")}
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 XuLan ScreenPilot
same job, measured the same wayLet your AI agent operate any website through a real, logged-in browser session.
Your recent screen captures as structured JSON your AI agent can read. Local only, no network.
Operate your whole Scrip rewards program through AI agents.
Turn a screen recording into agent-readable annotated keyframes. MCP server + CLI on ffmpeg.
Turn any table into a real .xlsx or CSV file: numbers stay numbers, header frozen. Free, no storage.
Publish micro-apps from your AI with no account; operate them as real apps. Data stored in the EU.
Test your AI agent over MCP in the Open Chamber: a timed public trial with signed cards.
Self-hostable team wiki; agents read & write it via MCP; Atlas turns your repo into a cited wiki.
XuLan ScreenPilot — questions
Answers built from our own checks of this server.