Integration · Model Context Protocol

Your IDE meets a UX consultant that ships fix-ready code.

The Corexi MCP server lets Cursor, Claude Code, Windsurf, Replit and VS Code call Corexi directly. Research-backed rules at design time, code review before commit, production findings after you ship. No browser tab, no copy-paste.

Get your API key →Try a live review Setup guide →

CursorClaude CodeWindsurfReplit AgentVS Code

Cursor · Composercorexi MCP

Review this CTA before I commit. Use our design system.

<button className="bg-[#94a3b8]
  px-3 py-1.5 text-white">Subscribe</button>

✓Called review_code · 1.2s

3 FINDINGS · 1 CRITICAL

AAContrast 2.1:1 fails WCAG AA. Use var(--color-primary).

44Tap target 36px, needs ≥44px (Apple HIG, WCAG 2.5.5).

⌨No focus-visible ring. WCAG 2.4.7.

<button className="bg-[var(--color-primary)]
  min-h-11 px-4 text-white
  focus-visible:ring-2">Subscribe</button>

MCP tools

IDEs supported

50/mo

LLM reviews free

Credit card

Two moments

Build it right, then keep it right.

Nine tools. Four for the moment before the bug ships, five for the moment after someone files it.

Build-time

Catch issues before they exist.

Your IDE asks Corexi for the right pattern, copy and structure before the first line of UI is written.

get_ux_rules

~50 research-backed rules. WCAG, NN/g, Baymard, Fitts — with citations.

get_ux_checklist

Pre-flight checklist for the surface you're about to build.

review_code50/mo

Send a snippet, get findings + fix-ready code in your design tokens.

review_screenshotshared quota

Vision-LLM review of a mockup or Figma export at design stage.

Post-deploy

Fix what production tells you.

Your IDE pulls the latest scan, narrows to the highest-impact issue, and lands fix-ready code in your editor.

list_sites

Sites registered to your account.

get_latest_scan

Latest UX Score + Lighthouse perf / a11y / SEO.

get_findings

Prioritized findings, filterable by severity, status or verified-by-rule.

trigger_scanscan scope

Kick off a fresh scan from inside your editor.

get_scan_job

Poll an async scan job without blocking the IDE.

What it looks like

Three real prompts, three real outputs.

Every scenario below is one tool call. Your AI agent picks the tool; you stay in flow.

Before you buildscenario

I'm about to build a checkout form. What should I get right the first time?

get_ux_checklist()

12 surface checks

Single-column layout, autofill attributes, error placement…

8 applicable rules

Severity-tagged: REQUIRED / RECOMMENDED / OPTIONAL.

Citations attached

Each rule cites WCAG · Baymard · NN/g.

Before you commitscenario

Review this CTA button JSX before I push. Use our design system.

review_code()

3 findings

Contrast fails AA, tap target 36px, no focus-visible ring.

Token-aware fix

Fix uses var(--color-primary), var(--space-md). Your tokens.

Rule cited

WCAG 1.4.3, Apple HIG tap targets, WCAG 2.4.7.

After you shipscenario

What's the highest-impact UX issue on corexi.ai right now?

get_findings()

Critical · /pricing

Monthly toggle has no aria-label — announced as 'button'.

Verified

axe-core confirmed the violation. Lighthouse a11y 87/100.

Drop-in fix

Ready Toggle with aria-checked + aria-label.

Setup

Connect in 60 seconds.

Cursor, VS Code and Claude Desktop install in one click. Claude Code, Windsurf and Replit get a single command or copy-ready config.

Generate an API key

Drop the snippet

Paste the JSON into .cursor/mcp.json or your IDE's equivalent.

Ask anything

Try: "Review this button." Or "What's the latest UX score on my homepage?"

Buttons install Corexi with a YOUR_API_KEY placeholder. Generate a real key at Settings → API Keys (free, instant for MCP signups) and swap it in once.

Cursor
One-click install
Add to Cursor
VS Code
One-click install
Add to VS Code
Claude Desktop
Opens Claude with our connector pre-filled
Add to Claude
Claude Code
One terminal command
Windsurf
Paste into mcp_config.json
~/.codeium/windsurf/mcp_config.json
Replit Agent
Paste into your Replit MCP config

Why it's safe to give to your IDE

Built for production teams.

Owner-only auth

Every call carries a Bearer key, verified server-side (SHA-256 + per-key salt, constant-time compare). No anonymous MCP traffic.

Telemetry that respects you

We log call duration, status and structured args. We never store raw code snippets, images, or anything you didn't ask us to keep.

Design-system aware

Pass your site_id and reviews inject your registered design tokens. Fixes return var(--your-token), not hardcoded hex/px.

Generous free tier

50 LLM-powered reviews per month per key. All read tools unlimited. trigger_scan respects your plan's monthly cap.

Ready when you are

Stop alt-tabbing. Stay in your editor.

Generate a key in under a minute, paste the snippet, and your AI agent gets a UX consultant + production-scan API for free.

Get your API key →See the platform