uisight

Your AI can already see the screen. It just can't measure it.

Screenshots make an agent guess: "that heading looks a bit faint." uisight makes it know:

- from a screenshot:  "the heading looks a little washed out, maybe adjust the color?"
+ from uisight:       INVISIBLE TEXT 1.04:1 — span.bg-gradient-to-r "your headline"
+                     (text rgba(255,255,255,.5) / bg rgb(247,247,248))

One is an impression. The other is a measurement with a selector attached — the agent fixes that element instead of hunting for it.

uisight is an MCP server for web and responsive UIs (Claude Code, Cursor, Antigravity, anything that speaks MCP). It runs live mobile + desktop sessions side by side, measures what it finds, and puts you and the agent in front of the exact same screen.

Built by a solo founder who got tired of taking phone screenshots, pasting them into chat, and typing "the button looks broken, can you see it?"

The live panel: desktop + mobile sessions of the same site, URL-synced. Inspect runs on every screen; findings come back per device. Your AI sees this exact view through MCP.

What makes it different

The measurement engine is the heart: instead of your AI burning tokens squinting at screenshots, inspect returns findings like

[mobile · Pixel 7 · light] https://yourapp.com/
  INVISIBLE TEXT 1.04:1 — span.bg-gradient-to-r "your headline" (text rgba(255,255,255,.5) / bg rgb(247,247,248))
  BUTTON a.text-white "Get Started" → text/background contrast 3.35:1
  touch target below 44px 180x23 — "read the guide"

Text findings are cheap, precise, and directly actionable — your AI fixes the exact selector instead of guessing.

"My agent already does this"

Fair — and partly true. Computer use, browser tools and most agent harnesses can already open a page and take a screenshot. That's the part uisight doesn't try to replace. Three things are still missing:

1. Looking isn't measuring. A vision model reading a screenshot cannot tell you a contrast ratio. It can't tell 4.6:1 (fine) from 4.3:1 (fails WCAG AA) — they look identical. It won't notice that a tap target is 41px instead of 44px, or that an element renders identically in light and dark mode because its color is hard-coded. uisight computes these from the live DOM: alpha-composited backgrounds, gradient text, oklch() colors and all.

2. Screenshots cost more and say less. A mobile screenshot is roughly 1,500 tokens of pixels the model has to interpret. The equivalent inspect result is a few hundred tokens of facts it can act on directly. Someone put it perfectly under the launch thread: "it burns some tokens but it manages." This is the version that doesn't burn them.

3. Nobody's watching with you. In the usual setup the agent looks at the page alone and reports back. Here you both watch the same live session — you see what it does as it does it, and when you spot something, you pin it (📌) with a note and the agent reads your note plus that exact frame. No more describing a bug in words.

Scope note: uisight is for web and responsive UIs. For native iOS/Android app control, Argent is excellent and does far more than we do there.

Quickstart

# one-shot audit: PNGs + gallery + report for iPhone/Pixel/desktop, light+dark
npx uisight https://yourapp.com --theme both

# live panel: mobile + desktop side by side, you browse, AI watches (and vice versa)
npx uisight-panel http://localhost:3000

The one-shot audit produces a device × theme gallery with findings per card:

Hook it into your AI (MCP)

# Claude Code
claude mcp add --scope user uisight -- npx -y uisight-mcp

For Cursor / Antigravity / other MCP hosts, add to your MCP config:

{ "mcpServers": { "uisight": { "command": "npx", "args": ["-y", "uisight-mcp"] } } }

Then just tell your agent: "look at my app with uisight". The panel server starts automatically when needed.

MCP tools

Turkish tool names available with UISIGHT_LANG=tr (ekrani_gor, denetle, ...).

The panel (human side)

npx uisight-panel <url> opens a browser page at localhost:5055:

• Mobile + desktop side by side, both live, URL-synced
• Click = tap on that device · wheel = scroll · type after clicking
• Per-pane device switcher, shared light/dark toggle
• Inspect button runs the measurement engine on every screen
• 📌 Pin: type a note, pin it — your AI reads note + screenshot via marks. No more "let me describe what I'm seeing."

Works inside VS Code / Antigravity via Simple Browser: Show → http://localhost:5055.

What it checks

• Invisible text (contrast < 1.6:1) and WCAG AA contrast failures — alpha-composited backgrounds, gradient text, oklab()/oklch() colors all handled
• Touch targets below 44px (mobile profiles only; inline text links exempt by width, per WCAG)
• Horizontal overflow with the offending elements
• Text below 12px, images without alt
• Theme drift: elements identical in light and dark = likely hard-coded colors
• Console/JS errors and failed network requests per device

And the honest limit: automated checks cannot see design mistakes — a collided header measures fine. That's why see_screen exists and why the report says "eyeball the PNGs."

Notes & limitations

• iPhone profiles run on real WebKit (Safari's engine) — close to iOS, but not an iOS Simulator.
• Browsers are downloaded once by Playwright on first run (npx playwright install chromium webkit if you want to pre-warm).
• Everything runs locally — no cloud, no account, your screens never leave your machine.
• v0.1 ships English surfaces over an internal codebase originally written in Turkish (being migrated). Contributions welcome; variable names may surprise you until v0.2.

License

MIT © SoloLabs