UXMUXMachine
Try it with a URL Sign in ESEN

Check your site after every AI change.

UXMachine opens it in a real browser, on desktop and mobile, and tells you what appeared since the last measurement, what is still there and what it couldn't check. Every measurement is kept in your project's UX memory, and your agent reads it before calling anything done.

Connect your agentSee real reports

10 free credits when you sign up. No card.

Works withLovable
  • Claude
  • Claude Code
Cursor
  • Grok
  • Grok Bot
  • ChatGPT
Coming soon
  • Bolt
  • Replit

Where it helps

Before you publish

With Claude Code or Cursor, measure the version on your computer. Whatever it finds, you fix before anyone sees it.

How your local version is measured ↓

With your site live

Ask your agent to measure it. If it works on your code, it makes the change and measures again until it is no longer observed.

Measure my site with UXMachine and tell me what to change.

UXMachine · 10 pages, at 1280 and 390 px · low contrast on 3 · report

Connect your tool ↓

Before you publish

Measure your local version

Your agent measures the site on your computer before you publish it. Works with Claude Code and Cursor.

  1. Your agent opens a temporary tunnel to your local server. It only needs Node.
  2. UXMachine measures that address just like a published site.
  3. The tunnel closes on its own after 30 minutes. Anyone with just the address cannot open your site.

The measurement is marked as local. It uses 1 credit, like any other.

Connect it in two minutes

Pick your tool. The first time, a UXMachine window opens so you can authorize it with your account; if you don't have one, you can create it there.

Lovable

  1. In your Lovable project, open Connectors → Add MCP server and enter this address: https://uxmachine.app/mcp
  2. In the UXMachine window, sign in (or create your account) and click "Authorize".
  3. In your site's project chat, not on the Lovable home screen, paste: "Using the UXMachine connector, measure my published site and give me the report link. Don't change any code."

Step-by-step guide to connect Lovable

Claude (web, desktop and mobile)

  1. In Claude, open Settings → Connectors, click "Add" and choose "Add custom connector".
  2. Enter the name UXMachine and this address: https://uxmachine.app/mcp. Click "Continue" and then "Add".
  3. In the UXMachine window, sign in (or create your account) and click "Authorize".
  4. In a new chat, ask: "Measure https://your-site.com with UXMachine and tell me what was observed and what could not be checked."

Step-by-step guide to connect Claude

Claude Code

  1. In your terminal, run: claude mcp add --transport http uxmachine https://uxmachine.app/mcp
  2. Inside Claude Code, type /mcp and choose uxmachine.
  3. Click "Authenticate". The UXMachine window opens in your browser.
  4. Click "Authorize". Go back to Claude Code and ask for a measurement.

Step-by-step guide to connect Claude Code

Cursor

  1. In Cursor, open Customize → MCPs → New MCP Server and paste this into mcp.json: {"mcpServers":{"uxmachine":{"url":"https://uxmachine.app/mcp"}}}
  2. Click "Authenticate". In the UXMachine window, click "Authorize" and then "Open Cursor".
  3. In Cursor's chat, use Agent mode.
  4. When Cursor asks for permission to use medir and estado, click "Run".

Grok

  1. In Grok, open the connectors page and click "New Connector".
  2. Choose "Custom", enter UXMachine as the name and this address as the "Server URL": https://uxmachine.app/mcp
  3. In the UXMachine window, sign in (or create your account) and click "Authorize".
  4. In a new chat, ask: "Measure the home page of https://yoursite.com with UXMachine."

Tested with the SuperGrok plan. Grok Bot uses the same connectors: once you add UXMachine on grok.com, Grok Bot can measure too.

ChatGPT

  1. In ChatGPT, open Settings → Plugins → Browse directory, click "Add" and choose "Add custom MCP server".
  2. Enter the name UXMachine and this address: https://uxmachine.app/mcp. Leave "OAuth", tick "I understand and want to continue" and click "Create as a plugin".
  3. In the UXMachine window, sign in (or create your account) and click "Authorize".
  4. In a new chat, ask: "Measure https://your-site.com with UXMachine and tell me what was observed and what could not be checked."

Tested with the Plus plan. From ChatGPT you cannot measure the version on your own computer.

Step-by-step guide to connect ChatGPT

How it works

You ask

"Measure the home page with UXMachine." Your agent sends us the address.

We measure

We open the page in a real browser, at 1280×800 and 390×844, on up to 11 pages of the site. It takes a few minutes.

Your agent acts

It reads the report, tells you what to change and, after the change, measures again.

What we observe, on real sites

Reports on public pages. They imply no commercial relationship, endorsement or approval.

Attio

The “email” field is declared as text. Judging by its name, it calls for an email address.

See the report →

PostHog

We found 1 menu that opens and closes without saying which of the two states it is in.

See the report →

Simple Analytics

On all 11 pages we reviewed, the first screen has links and buttons that share the same background, text color and…

See the report →

See all the cases →

Free to start

You get 10 credits when you sign up. Each measurement uses 1. Up to 10 measurements a day, one at a time. Measurements we cannot make use none.

What each observation contains

  • What is observed and where: the page, the window width and the element, with the measurement it comes from.
  • The observable state to bring it to.
  • How to check that it got there: which measurement runs again and which value counts as reached.
  • If we cannot state something, we say so and say why.

Measuring again

With an account, each measurement is compared on its own with the previous one of the same site, even if you made it with another tool or from the website. Each check comes back with one of these states: "Still observed", "No longer observed", "New", "Observed again" or "Not comparable", with its reason. "No longer observed" means it did not appear in the new measurement, not that it is solved. You can also compare your local version with the published one.

What it measures and what it does not

We measure what the page shows when it loads, in two windows (1280×800 and 390×844) and on up to 11 pages of the site. Only checks with an exact state that can be measured again the same way come out through this channel; they are on this list: /en/agents/rules. We do not fill in forms, we do not enter password-protected areas and we do not follow what happens after a click. We do not give opinions on design, copy or brand. This does not replace an audit or testing with people.

robots.txt and other people's sites

The channel respects robots.txt: if a site does not allow us to visit it, we do not measure it and we tell you so. Only ask for measurements of sites that are yours or that you have permission to review.

Try it on your next change.

Connect your agent

What we keep when you connect an agent: /en/privacy#agent-channel