cd /news/developer-tools/show-hn-hands-rust-mcp-cli-that-sees… · home topics developer-tools article
[ARTICLE · art-107488] src=news.ycombinator.com ↗ pub= topic=developer-tools verified=true sentiment=· neutral

Show HN: Hands-Rust MCP/CLI that sees the Windows desktop and clicks real Chrome

Ryan-AI-Studios released Hands, an open-source Rust MCP/CLI that lets coding agents control a real Windows desktop and Chrome browser via OS-level input, avoiding automation flags. The tool, available on GitHub under MIT license, supports tools like observe, click, type, and scroll, and is designed for personal research tasks, but it is not a sandbox and has best-effort safeguards against unintended actions.

read2 min views1 publishedAug 23, 2026

I built Hands because I wanted a coding agent to use this Windows PC and a real Chrome profile the way I do: look at the screen, move the real mouse, type, click , without turning Chrome into an automation browser.

It is a Rust MCP/CLI. A harness (Grok, Codex, Claude Code, OpenCode, etc.) calls tools like observe, click, type, scroll. Observe is a screenshot path plus a small element list (UIA + optional Chrome DOM ids). Click is OS SendInput on a Bézier path, not a Chrome DevTools click.

There is no Playwright, no Puppeteer, no remote debugging port. Daily Chrome is launched with no extra flags, or attached if it’s already open. Sites that key on CDP/automation flags mostly don’t see that. They can still see injected input (LLMHF_INJECTED).

A tiny unpacked Chrome extension can fuse page structure (chr: ids, listing cards) so the model isn’t guessing from pixels. Sideload is manual. Fusion dies if the service worker goes inactive; reload the card.

What it is good for: personal research on your own desk. “Find a Camry on cars.com,” read a page, fill a ZIP, dismiss a cookie banner.

What it is not: • Not a sandbox. It can click whatever is on screen, including checkout and Easy Apply. • Confirm-before-money is best-effort classification in the binary, not a guarantee. Prompt injection from the screenshot/DOM is real; the binary treats that text as untrusted, the model might not. • Not a CAPTCHA solver on daily Chrome. Two visible tries, then it yields and waits for the puzzle to go away. • Windows only. • Install is: build the exe, register a native-messaging host, sideload the extension, point an MCP client at hands mcp. README is the runbook. Missing an API key does not fail the build; do_task is optional. • Logs live under %LOCALAPPDATA%\hands\logs. The extension asks for so it can map the tab you’re looking at.

Repo: https://github.com/Ryan-AI-Studios/hands (MIT) Happy to answer how observe/fusion/the fence work. If you try it, /Break is the kill switch.

Comments URL: [https://news.ycombinator.com/item?id=49405405](https://news.ycombinator.com/item?id=49405405)

Points: 1

── more in #developer-tools 4 stories · sorted by recency
── more on @ryan-ai-studios 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-hands-rust-m…] indexed:0 read:2min 2026-08-23 ·