uisightBLOCK
Your AI can already see the screen — it just can't measure it. Live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) reporting findings as text, and a panel you and your agent share. MCP server for web/responsive UIs.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/sololabstr/uisight/actions/workflows/ci.yml) [](https://www.npmjs.com/package/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
589bc79e666aOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add uisight -- npx -y [email protected]
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (8 observation(s))
- Shell
- declared (4 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (14)
exec(command, p === 'win32' ? { shell: 'cmd.exe' } : {}, (e) => {exec(command, p === 'win32' ? { shell: 'cmd.exe' } : {}, (e) => {.map((q) => `http://localhost:${q} http://127.0.0.1:${q}`).join(' ');const BASE = `http://127.0.0.1:${PORT}`;const BASE = `http://127.0.0.1:${PORT}`;.vscodeignore
return new Function('return ' + ext.slice(i, j).replace('function gomuluHtml', 'function'))();`http://127.0.0.1:${port}/`,`http://127.0.0.1:${port}/`,@modelcontextprotocol/sdk, playwright, zod
uisight
uisight
uisight
Gates applied: no_behavioural_pass.
589bc79e666afull audit observations/trust-audit/mcp-server/sololabstr__uisight.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 589bc79e666a | BLOCK | D | 69 | first audit |
Questions
What is the uisight MCP server?
Your AI can already see the screen — it just can't measure it. Live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) reporting findings as text, and a panel you and your agent share. MCP server for web/responsive UIs.
Is uisight safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does uisight need?
It reads UISIGHT_MAX_IMAGE_TOKENS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does uisight run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as uisight-panel at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (589bc79e666a), read on 2026-10-12. The repository is watched and re-audited when it changes.