See Corexi run on your own product, live, in 15 minutes.
Book a demoThe Corexi MCP server gives any Model Context Protocol agent (Cursor, Claude Code, Windsurf, Replit, VS Code) your runs, findings and fix-ready code, without leaving the editor.
Open Corexi → Settings → API Keys → click New API key. Give it a memorable name (e.g. “Cursor on laptop”), then copy the key from the reveal modal. It's only shown once.
Sign up to create your first key →Keys start with crxi_live_. We store only a salted SHA-256 hash; if you lose a key you must revoke and re-issue.
Scopes
mcp:read: granted by default. Lets the agent read sites, scans, findings, UX rules, runreview_codeandreview_screenshot.scan:trigger: opt-in. Lets the agent start Autopilot runs on production viatrigger_scan(counts against your plan). Tick the box when you create the key.Replace crxi_live_YOUR_KEY_HERE with the key you just generated.
.cursor/mcp.json{
"mcpServers": {
"corexi": {
"url": "https://corexi.ai/api/mcp",
"headers": {
"Authorization": "Bearer crxi_live_YOUR_KEY_HERE"
}
}
}
}Create the file in your project root or in your home directory under ~/.cursor/mcp.json for global access. Cursor reloads MCP servers automatically when the file changes.
.mcp.json in the project root (or: claude mcp add --transport http corexi https://corexi.ai/api/mcp --header "Authorization: Bearer crxi_live_YOUR_KEY_HERE"){
"mcpServers": {
"corexi": {
"type": "http",
"url": "https://corexi.ai/api/mcp",
"headers": {
"Authorization": "Bearer crxi_live_YOUR_KEY_HERE"
}
}
}
}Restart Claude Code after editing. Run /mcp to confirm Corexi is connected.
~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"corexi": {
"serverUrl": "https://corexi.ai/api/mcp",
"headers": {
"Authorization": "Bearer crxi_live_YOUR_KEY_HERE"
}
}
}
}Restart Windsurf, then open Cascade and check the MCP servers panel.
.vscode/mcp.json{
"servers": {
"corexi": {
"type": "http",
"url": "https://corexi.ai/api/mcp",
"headers": {
"Authorization": "Bearer crxi_live_YOUR_KEY_HERE"
}
}
}
}Requires the GitHub Copilot Chat extension or any MCP-compatible chat client. Reload window after editing.
Replit Agent settings → MCP serversServer URL: https://corexi.ai/api/mcp
Auth header: Authorization: Bearer crxi_live_YOUR_KEY_HEREAdd via the Replit Agent settings UI; configuration format may evolve as Replit ships its MCP support.
Once connected, your AI agent calls these tools on its own when you ask UX-related questions. You don't need to invoke them manually.
Use while writing code. Your agent applies Corexi's research-backed UX patterns from the first commit. No need to register a site or run a scan first.
get_ux_rulesNo scan neededReturns Corexi's research-backed UX rules. Filter by category, severity, finding type, or free text.
Try asking
"What are the rules for designing accessible CTAs?"
Returns
Each rule: what / why / how + do/dont examples + code snippet + research citations (WCAG, NN/g, Baymard, Fitts, Miller, BDA, CUD).
get_ux_checklistNo scan neededReturns a pre-flight checklist for a specific surface (checkout, modal, hero, pricing, navigation, etc.).
Try asking
"Give me the checklist before I implement the checkout form."
Returns
Surface-specific extra checks + applicable Corexi rules with severity tags (required / recommended / optional).
review_codeOpen beta · token-awareLLM-powered review of a code snippet against Corexi's 9 categories and the neurodiversity lenses. Catches issues BEFORE you commit. Pass an optional site_id to inject your registered design tokens; fix_code will use var(--your-token) instead of hardcoded hex/px.
Try asking
"Review this checkout button JSX for UX issues before I commit."
Returns
Prioritized findings with evidence, research citations, and copy-paste fix_code snippets that match your design system. No practical limit during the open beta; a per-key monthly quota starts when plans do.
review_screenshotShared quotaVision-LLM review of a single image (design mockup, Figma export, local screenshot). Validates designs at the mockup stage. Accepts site_id for design-token-aware fixes.
Try asking
"Review this Figma export of the new pricing page."
Returns
Findings with bounding boxes, severity, and recommendations. Shares one bucket with review_code, which is not capped during the open beta.
Pull live data from your registered Corexi sites: scans, scores, and prioritized findings.
list_sitesList the sites registered to your Corexi account.
Try asking
"What Corexi sites do I have?"
Returns
Site name, domain, surface, dev environment, scan frequency.
get_latest_scanFetch the latest scan summary for a site.
Try asking
"What's the UX score on my pricing page?"
Returns
UX Score, breakdown by category, pages scanned, run timestamp.
get_findingsList prioritized findings for a scan, filterable by severity and status.
Try asking
"Show me the top 5 high-severity issues on my homepage scan."
Returns
Title, evidence, recommendation, fix-ready code, impact score.
trigger_scanscan:trigger scopeStart an Autopilot run on a product you own, from inside the IDE: AI walks it like a new user, maps the flows and scores every screen it reaches. Subject to plan limits + cooldowns.
Try asking
"Run Autopilot on my app and tell me what changed since last week."
Returns
job_id at once; get_scan_job(job_id) reports the run (10–40 min) and then scan_id, UX score, screens, findings. Use get_findings(scan_id) to inspect issues.
get_scan_jobFollow a run started with trigger_scan, without blocking the IDE: its steps as they happen, or wait for the end.
Try asking
"Is the run done yet?"
Returns
Status, steps and screens so far; when done, scan_id, UX score, screens and findings.
get_run_diffWhat a run changed against the one before it. Use it after a deploy.
Try asking
"What did the last deploy fix?"
Returns
Findings fixed, not seen this run, new, back and still open; before and after screenshots for fixed ones.
A typical session in Cursor combines build-time and post-deploy tools:
“I'm about to build a checkout form. What should I watch out for?”
→ Cursor calls get_ux_checklist with surface: "checkout_form" → 15 rules + 6 surface-specific checks land in chat.
“Generate the form following these rules.”
→ Cursor writes the JSX with persistent labels, inline error validation, autocomplete attributes, 44px touch targets, and ARIA error association, out of the box.
Before commit: “Review this form before I push.”
→ Cursor calls review_code with the JSX → Corexi's LLM applies the 11-category rubric → returns findings + fix snippets so you can patch inline before committing.
After deploy: “Run Autopilot on production and tell me if I shipped any regressions.”
→ Cursor calls trigger_scan with the right site_id → Autopilot walks the product (10–40 min) → get_scan_job returns the new score and finding count, plus a hint to call get_findingsfor the details.
“Show me the high-severity findings and patch them one by one.”
→ Cursor calls get_findings filtered by severity → walks through eachfix_codeand applies it inline in the IDE.
429 with a Retry-After header.401 immediately.last_used_at for each key (no payloads). Use it to detect stale or unused keys.Your key is missing, malformed, or revoked. Double-check the Authorization header includes the literal word "Bearer" before your key. Generate a new key in Settings → API Keys if needed.
You hit the rate limit (60 requests/minute sustained or 10 requests/second burst). The response Retry-After header tells you when to retry. Spread out tool calls or upgrade your plan.
Use list_sites first to get a valid site_id. Sites are scoped to your account; you can only access ones you registered in Corexi.
Check the Cursor settings → Tools and Integrations → MCP. If Corexi shows red, click it for the error log. Most often: malformed JSON or missing trailing comma in mcp.json.
Keys are unrecoverable by design; only a salted hash is stored. Revoke the lost key and generate a new one in Settings → API Keys.
Coming next: a dedicated dashboard panel for MCP usage analytics + IDE connection status, async scan polling for long-running jobs, and a marketplace listing in Cursor. Need something specific? Get in touch.