Flintrail runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 29 Oct 2026.
Drive a real Chrome live, record a flow once, replay it in milliseconds without an LLM.
What the code does
We read the source, 4 d 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.
const child = spawn(process.execPath, [target.entry, ...args], {
const serverIn = (dir) => path.join(dir, 'node_modules', cfg.package, cfg.server);
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 Flintrail
same job, measured the same wayRecord a browser flow once with a model, then compile it to a Playwright spec that needs no model.
Watch your AI drive a real Chrome live, point, approve, or take the wheel from your phone.
Drive your real, logged-in Chrome (many profiles, parallel tabs) from any MCP client. Local only.
Drive your real, logged-in Chrome/Edge from AI agents over CDP. Faster. Sharper.
Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.
Drive your real, logged-in Chrome from any MCP client — even from a remote machine, no inbound port.
End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.
Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.
Flintrail — questions
Answers built from our own checks of this server.