Uimax Mcp
Brings Puppeteer, Lighthouse, and axe-core audits directly into Claude Code so you can review and fix frontend issues without leaving the conversation. One command runs the full pipeline: screenshot capture, accessibility violations, Core Web Vitals, SEO checks across 18 signals, and AST-based code analysis for 25+ anti-patterns. It grades everything with letter scores (A+ through F) and feeds Claude a structured review methodology so it can act like a senior frontend engineer. Then it edits your files to implement the fixes. The verify_fixes tool re-audits after changes and shows before/after grade transitions. Works on localhost, staging, or production URLs. No API keys, runs entirely through the MCP stdio transport using your existing Claude Pro plan.
- GitHub stars
- 7
- tools
- 37
- transport
- STDIO
- last updated
- Mar 27, 2026
Tools
37 toolsPublic tool metadata for what this MCP can expose to an agent.
review_uiThe main tool. Full automated pipeline: screenshot + Lighthouse + axe-core + performance + SEO + code analysis + Report Card (A+-F letter grades) + expert review methodology. Auto-saves to review history.
The main tool. Full automated pipeline: screenshot + Lighthouse + axe-core + performance + SEO + code analysis + Report Card (A+-F letter grades) + expert review methodology. Auto-saves to review history.
No parameter schema in public metadata yet.
verify_fixesRe-run the full audit after applying fixes. Compares against the previous review and shows a before/after Report Card with grade transitions, resolved issue count, and verdict (improved/regressed/mixed).
Re-run the full audit after applying fixes. Compares against the previous review and shows a before/after Report Card with grade transitions, resolved issue count, and verdict (improved/regressed/mixed).
No parameter schema in public metadata yet.
compare_sitesCompetitive benchmarking — audit two URLs side-by-side. Returns screenshots of both sites plus a comparison Report Card with grades for Accessibility, Performance, SEO, and weighted Overall score.
Competitive benchmarking — audit two URLs side-by-side. Returns screenshots of both sites plus a comparison Report Card with grades for Accessibility, Performance, SEO, and weighted Overall score.
No parameter schema in public metadata yet.
quick_reviewFast design-only review. Screenshot + focused design methodology. No code analysis or performance audit.
Fast design-only review. Screenshot + focused design methodology. No code analysis or performance audit.
No parameter schema in public metadata yet.
export_reportGenerate a standalone HTML report with everything embedded. Now includes Report Card grade cards and SEO section. Dark themed, zero dependencies. Share with your team.
Generate a standalone HTML report with everything embedded. Now includes Report Card grade cards and SEO section. Dark themed, zero dependencies. Share with your team.
No parameter schema in public metadata yet.
screenshotCapture a high-resolution PNG screenshot of any URL.
Capture a high-resolution PNG screenshot of any URL.
No parameter schema in public metadata yet.
responsive_screenshotsScreenshots at mobile (375px), tablet (768px), and desktop (1440px) viewports.
Screenshots at mobile (375px), tablet (768px), and desktop (1440px) viewports.
No parameter schema in public metadata yet.
check_dark_modeCompare light mode vs dark mode (emulated). Returns both screenshots + difference percentage.
Compare light mode vs dark mode (emulated). Returns both screenshots + difference percentage.
No parameter schema in public metadata yet.
compare_screenshotsPixel-level diff using pixelmatch. Returns both screenshots + red-highlighted diff image + exact pixel difference %.
Pixel-level diff using pixelmatch. Returns both screenshots + red-highlighted diff image + exact pixel difference %.
No parameter schema in public metadata yet.
semantic_compareAI-powered visual comparison. Captures before/after + pixel diff, returns structured methodology for Claude to evaluate whether changes match the intended design request.
AI-powered visual comparison. Captures before/after + pixel diff, returns structured methodology for Claude to evaluate whether changes match the intended design request.
No parameter schema in public metadata yet.
lighthouse_auditFull Google Lighthouse audit — Performance, Accessibility, Best Practices, SEO scores + failing audits.
Full Google Lighthouse audit — Performance, Accessibility, Best Practices, SEO scores + failing audits.
No parameter schema in public metadata yet.
seo_auditDedicated SEO audit checking 18 signals: meta title/description, heading hierarchy, Open Graph, Twitter cards, structured data (JSON-LD), canonical URLs, image alt text, viewport meta, lang attribute, and more.
Dedicated SEO audit checking 18 signals: meta title/description, heading hierarchy, Open Graph, Twitter cards, structured data (JSON-LD), canonical URLs, image alt text, viewport meta, lang attribute, and more.
No parameter schema in public metadata yet.
pwa_auditPWA readiness: installable, service worker, HTTPS, manifest, offline capability.
PWA readiness: installable, service worker, HTTPS, manifest, offline capability.
No parameter schema in public metadata yet.
security_auditSecurity analysis: HTTPS, CSP, mixed content, vulnerable JS libraries, external links without noopener.
Security analysis: HTTPS, CSP, mixed content, vulnerable JS libraries, external links without noopener.
No parameter schema in public metadata yet.
unused_codeFind unused JavaScript and CSS with exact byte savings per resource.
Find unused JavaScript and CSS with exact byte savings per resource.
No parameter schema in public metadata yet.
lcp_optimizationDeep LCP analysis: what the element is, resource load time, render delay, TTFB, optimization suggestions.
Deep LCP analysis: what the element is, resource load time, render delay, TTFB, optimization suggestions.
No parameter schema in public metadata yet.
resource_analysisFull resource breakdown by type, transfer sizes, request count, top 10 largest, render-blocking resources.
Full resource breakdown by type, transfer sizes, request count, top 10 largest, render-blocking resources.
No parameter schema in public metadata yet.
performance_auditCore Web Vitals via Performance API: FCP, LCP, CLS, TBT, DOM node count, JS heap size.
Core Web Vitals via Performance API: FCP, LCP, CLS, TBT, DOM node count, JS heap size.
No parameter schema in public metadata yet.
accessibility_auditaxe-core WCAG 2.1 Level A & AA audit. Violations grouped by severity with fix instructions.
axe-core WCAG 2.1 Level A & AA audit. Violations grouped by severity with fix instructions.
No parameter schema in public metadata yet.
analyze_codeAST-based analysis (TypeScript compiler API) for 25+ rules. Zero false positives on string literals. Falls back to regex for non-JS files. Configurable via .uimaxrc.json.
AST-based analysis (TypeScript compiler API) for 25+ rules. Zero false positives on string literals. Falls back to regex for non-JS files. Configurable via .uimaxrc.json.
No parameter schema in public metadata yet.
navigateNavigate to a URL, wait for network idle. Returns page info + screenshot.
Navigate to a URL, wait for network idle. Returns page info + screenshot.
No parameter schema in public metadata yet.
clickClick an element by CSS selector. Returns screenshot after click.
Click an element by CSS selector. Returns screenshot after click.
No parameter schema in public metadata yet.
type_textType into input fields. Options: clearFirst, pressEnter. Returns screenshot after.
Type into input fields. Options: clearFirst, pressEnter. Returns screenshot after.
No parameter schema in public metadata yet.
select_optionSelect a dropdown option by value. Returns screenshot after.
Select a dropdown option by value. Returns screenshot after.
No parameter schema in public metadata yet.
scrollScroll by pixel amount or to a specific element. Returns screenshot after.
Scroll by pixel amount or to a specific element. Returns screenshot after.
No parameter schema in public metadata yet.
wait_forWait for an element to appear in the DOM. Returns tag name and text content.
Wait for an element to appear in the DOM. Returns tag name and text content.
No parameter schema in public metadata yet.
get_elementGet element details: attributes, bounding box, computed styles, visibility.
Get element details: attributes, bounding box, computed styles, visibility.
No parameter schema in public metadata yet.
capture_consoleCapture all console messages (log, warn, error, info, debug) + uncaught exceptions during page load.
Capture all console messages (log, warn, error, info, debug) + uncaught exceptions during page load.
No parameter schema in public metadata yet.
capture_networkCapture all network requests with status, size, timing, resource type. Summary grouped by type.
Capture all network requests with status, size, timing, resource type. Summary grouped by type.
No parameter schema in public metadata yet.
capture_errorsCapture JS exceptions, unhandled rejections, and failed resource loads.
Capture JS exceptions, unhandled rejections, and failed resource loads.
No parameter schema in public metadata yet.
crawl_and_reviewDiscover internal links from a URL and audit up to 10 pages — screenshot + axe-core + performance each.
Discover internal links from a URL and audit up to 10 pages — screenshot + axe-core + performance each.
No parameter schema in public metadata yet.
save_baselineSave current audit state to .uimax-history.json. Track scores over time.
Save current audit state to .uimax-history.json. Track scores over time.
No parameter schema in public metadata yet.
compare_to_baselineCompare current state vs previous baseline. Shows improvements and regressions with letter grade transitions.
Compare current state vs previous baseline. Shows improvements and regressions with letter grade transitions.
No parameter schema in public metadata yet.
check_budgetsEnforce performance budgets from .uimaxrc.json. Pass/fail for Lighthouse scores, Web Vitals, violation counts.
Enforce performance budgets from .uimaxrc.json. Pass/fail for Lighthouse scores, Web Vitals, violation counts.
No parameter schema in public metadata yet.
get_review_historyView past UIMax reviews for this project. Filter by URL, limit count. Now includes letter grades alongside scores.
View past UIMax reviews for this project. Filter by URL, limit count. Now includes letter grades alongside scores.
No parameter schema in public metadata yet.
get_review_statsAggregate statistics: total reviews, score trends, most common issues, most problematic files. Includes Code Quality grades.
Aggregate statistics: total reviews, score trends, most common issues, most problematic files. Includes Code Quality grades.
No parameter schema in public metadata yet.
review_diffCompare two specific reviews — new issues, resolved issues, score changes with letter grade transitions.
Compare two specific reviews — new issues, resolved issues, score changes with letter grade transitions.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
UIMax MCP
Turns Claude Code into a frontend expert that reviews and fixes your UI automatically.
-brightgreen){kind=icon}
One command — "review my UI at localhost:3000" — and it:
Details
- Repository
- github.com/prembobby39-gif/uimax-mcp
- Package
uimax-mcp- Transport
- STDIO
- Registry
- MCP registry, active