{ "markdown": "# UIMax MCP\n\n**Turns Claude Code into a frontend expert that reviews and fixes your UI automatically.**\n\n

\n \"npm\n \"npm\n \"license\"\n \"37\n \"463\n \"free\n

\n\nOne command — *\"review my UI at localhost:3000\"* — and it:\n\n1. **Sees your app** — captures a real screenshot via Puppeteer\n2. **Audits accessibility** — runs axe-core for WCAG 2.1 violations\n3. **Runs Lighthouse** — real Google Lighthouse scores (Performance, Accessibility, Best Practices, SEO)\n4. **Measures performance** — captures Core Web Vitals (FCP, LCP, CLS, TBT)\n5. **Audits SEO** — 18 checks: meta tags, Open Graph, Twitter cards, structured data, heading hierarchy, canonical URLs\n6. **Scans your code** — AST-based analysis for 25+ anti-patterns across accessibility, design, and code quality\n7. **Grades everything** — per-section Report Card with letter grades (A+ through F) for Accessibility, Performance, Best Practices, SEO, and Code Quality\n8. **Generates an expert review** — Claude acts as a senior frontend engineer with a baked-in review methodology\n9. **Implements the fixes** — edits your actual code files, starting from critical issues down\n10. **Tracks everything** — auto-saves review history so you can see progress over time\n\n**Works on any URL** — localhost, staging, production. Any site your machine can reach.\n\n**Free for all Claude Code users (Pro plan and above). No API keys. No extra costs. Just install and go.**\n\n```bash\nclaude mcp add uimax -- npx -y uimax-mcp\n```\n\n---\n\n## Quick Start\n\n### Install as MCP Server (for Claude Code)\n\n```bash\n# Add to Claude Code — that's it, no API keys needed\nclaude mcp add uimax -- npx -y uimax-mcp\n```\n\nThat's it. Now in any Claude Code conversation:\n\n```\nYou: Review the UI at http://localhost:3000, source code is in ./src\n\nClaude Code calls review_ui ->\n 1. Captures screenshot of your running app\n 2. Runs axe-core accessibility audit\n 3. Runs Google Lighthouse (Performance, A11y, Best Practices, SEO)\n 4. Measures Core Web Vitals\n 5. Runs dedicated SEO audit (18 checks)\n 6. Scans source code with AST-based analysis\n 7. Generates per-section Report Card (A+ through F letter grades)\n 8. Returns screenshot + all data + expert review methodology\n 9. Claude Code generates expert review (using YOUR Pro plan -- $0 extra)\n 10. Claude Code implements every fix automatically\n 11. Review saved to .uimax-reviews.json for tracking\n```\n\n### Install Globally\n\n```bash\nnpm install -g uimax-mcp\n```\n\n---\n\n## Tools (37)\n\n### Review Pipeline\n\n| Tool | Description |\n|------|-------------|\n| `review_ui` | **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. |\n| `verify_fixes` | **New in v0.9.0.** 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). Closes the review-fix-verify loop. |\n| `compare_sites` | **New in v0.9.0.** 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. |\n| `quick_review` | Fast design-only review. Screenshot + focused design methodology. No code analysis or performance audit. |\n| `export_report` | 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. |\n\n### Screenshots & Visual\n\n| Tool | Description |\n|------|-------------|\n| `screenshot` | Capture a high-resolution PNG screenshot of any URL. |\n| `responsive_screenshots` | Screenshots at mobile (375px), tablet (768px), and desktop (1440px) viewports. |\n| `check_dark_mode` | Compare light mode vs dark mode (emulated). Returns both screenshots + difference percentage. |\n| `compare_screenshots` | Pixel-level diff using `pixelmatch`. Returns both screenshots + red-highlighted diff image + exact pixel difference %. |\n| `semantic_compare` | **AI-powered visual comparison.** Captures before/after + pixel diff, returns structured methodology for Claude to evaluate whether changes match the intended design request. |\n\n### Lighthouse, Performance & SEO\n\n| Tool | Description |\n|------|-------------|\n| `lighthouse_audit` | Full Google Lighthouse audit — Performance, Accessibility, Best Practices, SEO scores + failing audits. |\n| `seo_audit` | **New in v0.8.0.** 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. Weighted scoring by impact. |\n| `pwa_audit` | PWA readiness: installable, service worker, HTTPS, manifest, offline capability. |\n| `security_audit` | Security analysis: HTTPS, CSP, mixed content, vulnerable JS libraries, external links without `noopener`. |\n| `unused_code` | Find unused JavaScript and CSS with exact byte savings per resource. |\n| `lcp_optimization` | Deep LCP analysis: what the element is, resource load time, render delay, TTFB, optimization suggestions. |\n| `resource_analysis` | Full resource breakdown by type, transfer sizes, request count, top 10 largest, render-blocking resources. |\n| `performance_audit` | Core Web Vitals via Performance API: FCP, LCP, CLS, TBT, DOM node count, JS heap size. |\n| `accessibility_audit` | axe-core WCAG 2.1 Level A & AA audit. Violations grouped by severity with fix instructions. |\n\n### Code Analysis\n\n| Tool | Description |\n|------|-------------|\n| `analyze_code` | 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`. |\n\n### Browser Interaction\n\n| Tool | Description |\n|------|-------------|\n| `navigate` | Navigate to a URL, wait for network idle. Returns page info + screenshot. |\n| `click` | Click an element by CSS selector. Returns screenshot after click. |\n| `type_text` | Type into input fields. Options: `clearFirst`, `pressEnter`. Returns screenshot after. |\n| `select_option` | Select a dropdown option by value. Returns screenshot after. |\n| `scroll` | Scroll by pixel amount or to a specific element. Returns screenshot after. |\n| `wait_for` | Wait for an element to appear in the DOM. Returns tag name and text content. |\n| `get_element` | Get element details: attributes, bounding box, computed styles, visibility. |\n\n### Debugging\n\n| Tool | Description |\n|------|-------------|\n| `capture_console` | Capture all console messages (log, warn, error, info, debug) + uncaught exceptions during page load. |\n| `capture_network` | Capture all network requests with status, size, timing, resource type. Summary grouped by type. |\n| `capture_errors` | Capture JS exceptions, unhandled rejections, and failed resource loads. |\n\n### Multi-Page\n\n| Tool | Description |\n|------|-------------|\n| `crawl_and_review` | Discover internal links from a URL and audit up to 10 pages — screenshot + axe-core + performance each. |\n\n### Baselines & Budgets\n\n| Tool | Description |\n|------|-------------|\n| `save_baseline` | Save current audit state to `.uimax-history.json`. Track scores over time. |\n| `compare_to_baseline` | Compare current state vs previous baseline. Shows improvements and regressions with letter grade transitions (e.g., \"D -> B+ (+22)\"). |\n| `check_budgets` | Enforce performance budgets from `.uimaxrc.json`. Pass/fail for Lighthouse scores, Web Vitals, violation counts. |\n\n### Review History\n\n| Tool | Description |\n|------|-------------|\n| `get_review_history` | View past UIMax reviews for this project. Filter by URL, limit count. Now includes letter grades alongside scores. |\n| `get_review_stats` | Aggregate statistics: total reviews, score trends, most common issues, most problematic files. Includes Code Quality grades. |\n| `review_diff` | Compare two specific reviews — new issues, resolved issues, score changes with letter grade transitions. |\n\n> **Every review is auto-saved.** When you run `review_ui`, the results are automatically persisted to `.uimax-reviews.json`. No manual save needed — just ask \"show me my review history\" anytime.\n\n---\n\n## Report Card (A+ through F)\n\nEvery `review_ui` run now generates a **per-section Report Card** with letter grades on a 13-tier scale:\n\n```\n┌─────────────────────────────────────────────────────┐\n│ REPORT CARD │\n├──────────────────┬──────────┬───────┬───────────────┤\n│ Section │ Score │ Grade │ Rating │\n├──────────────────┼──────────┼───────┼───────────────┤\n│ Accessibility │ 95 │ A │ Excellent │\n│ Performance │ 72 │ C- │ Below Average │\n│ Best Practices │ 88 │ B+ │ Very Good │\n│ SEO │ 61 │ D- │ Very Weak │\n│ Code Quality │ 83 │ B │ Good │\n└──────────────────┴──────────┴───────┴───────────────┘\n```\n\nGrades appear in:\n- **`review_ui` output** — Report Card table at the top of every review\n- **`export_report` HTML** — color-coded grade cards (green A -> red F)\n- **`compare_to_baseline`** — grade transitions showing improvement (e.g., `D -> B+ (+22)`)\n- **`get_review_history` / `get_review_stats` / `review_diff`** — grades alongside numeric scores for quick scanning\n\nThe grading scale: `A+` (97+) > `A` (93+) > `A-` (90+) > `B+` (87+) > `B` (83+) > `B-` (80+) > `C+` (77+) > `C` (73+) > `C-` (70+) > `D+` (67+) > `D` (63+) > `D-` (60+) > `F` (<60)\n\n---\n\n## AST-Powered Code Analysis\n\nThe `analyze_code` tool uses the **TypeScript compiler API** for `.ts/.tsx/.js/.jsx` files — catching bugs that regex misses with zero false positives.\n\n| Rule | What AST catches that regex misses |\n|------|-----------------------------------|\n| `react-hooks-conditional` | Hooks inside nested if/for/while/ternary — proper scope traversal |\n| `missing-key-prop` | `.map()` callbacks returning JSX without `key` — handles arrow/block bodies |\n| `empty-catch` | Empty catch blocks — not fooled by comments |\n| `any-type` | `any` in type positions only — ignores \"any\" in strings/comments |\n| `direct-dom-access` | `document.querySelector` etc. — proper call expression matching |\n| `console-log` | `console.log/warn/error` — not fooled by variable names containing \"console\" |\n| `inline-style` | JSX `style={}` attributes — proper attribute detection |\n\nFalls back to regex for file types that can't be AST-parsed and for rules without AST implementations (hardcoded colors, z-index, font sizes, etc.).\n\n---\n\n## Configuration\n\nCreate a `.uimaxrc.json` in your project root to customize code analysis and performance budgets:\n\n```json\n{\n \"rules\": {\n \"console-log\": \"off\",\n \"magic-number\": \"off\",\n \"hardcoded-color\": \"warn\",\n \"inline-style\": \"error\"\n },\n \"severity\": {\n \"todo-fixme\": \"high\"\n },\n \"ignore\": [\n \"node_modules\",\n \"dist\",\n \"*.test.*\",\n \"*.spec.*\"\n ],\n \"budgets\": {\n \"lighthouse\": {\n \"performance\": 90,\n \"accessibility\": 95,\n \"bestPractices\": 90,\n \"seo\": 90\n },\n \"webVitals\": {\n \"fcp\": 1800,\n \"lcp\": 2500,\n \"cls\": 0.1,\n \"tbt\": 300\n },\n \"maxAccessibilityViolations\": 0,\n \"maxCodeIssues\": 10\n }\n}\n```\n\n- **`rules`** — Set any rule to `\"off\"`, `\"warn\"`, or `\"error\"`\n- **`severity`** — Override severity: `\"low\"`, `\"medium\"`, `\"high\"`, `\"critical\"`\n- **`ignore`** — Additional glob patterns to exclude from analysis\n- **`budgets`** — Performance thresholds enforced by the `check_budgets` tool\n\nUIMax searches for `.uimaxrc.json` in the target directory and up to 3 parent directories, so it works in monorepos.\n\n---\n\n## Prompts\n\nExpert review prompts that guide Claude's analysis:\n\n| Prompt | Use Case |\n|--------|----------|\n| `ui-review` | Comprehensive review (design + UX + a11y + perf + code) |\n| `responsive-review` | Responsive design review across viewports |\n| `quick-design-review` | Fast visual/UX feedback from a screenshot only |\n| `semantic-compare` | AI-powered before/after visual comparison |\n\n---\n\n## Example Workflows\n\n### Full Review (the main workflow)\n```\nYou: Review the UI at http://localhost:3000\n Source code is in ./src\n\nClaude: [Calls review_ui]\n [Captures screenshot, runs Lighthouse + axe + perf + code scan]\n [Generates 20+ findings with specific fixes]\n [Implements every fix automatically]\n [Auto-saves review to .uimax-reviews.json]\n```\n\n### Review Any Public Website\n```\nYou: Review the UI at https://stripe.com\n\nClaude: [Calls review_ui]\n [Full audit of the live production site]\n [Returns findings + recommendations]\n```\n\n### Track Progress Over Time\n```\nYou: Show me my review history\n\nClaude: [Calls get_review_history]\n [Shows table of past reviews: dates, scores, issue counts]\n\nYou: Compare my last two reviews\n\nClaude: [Calls review_diff]\n [Shows what improved ✅, what regressed ❌, new issues, resolved issues]\n\nYou: What are my most common issues?\n\nClaude: [Calls get_review_stats]\n [Shows trends, most common issues, most problematic files]\n```\n\n### Interact with Your App\n```\nYou: Navigate to localhost:3000, click the login button,\n type \"test@email.com\" in the email field\n\nClaude: [Calls navigate → click → type_text]\n [Returns a screenshot after each action]\n [Verifies each step visually]\n```\n\n### Deep Performance Analysis\n```\nYou: Find unused code on https://myapp.com\n\nClaude: [Calls unused_code]\n [Lists every unused JS/CSS file with byte savings]\n [Suggests what to tree-shake]\n\nYou: Why is my LCP slow?\n\nClaude: [Calls lcp_optimization]\n [Identifies the LCP element, breakdown of load time]\n [Specific optimization suggestions]\n```\n\n### Verify Fixes (Close the Loop)\n```\nYou: Review and fix my UI at localhost:3000\n\nClaude: [Calls review_ui → finds 14 issues → implements fixes]\n\nYou: Now verify the fixes worked\n\nClaude: [Calls verify_fixes]\n [Re-runs full audit → compares to previous review]\n\n Fix Verification — Before vs After\n | Metric | Before | After | Change |\n | Accessibility violations | 5 | 0 | ✅ -5 |\n | Code findings | 9 | 2 | ✅ -7 |\n | Total issues | 14 | 2 | ✅ -12 |\n\n Verdict: ✅ IMPROVED\n```\n\n### Competitive Benchmarking\n```\nYou: Compare my site vs stripe.com\n\nClaude: [Calls compare_sites]\n [Audits both URLs concurrently]\n [Returns screenshots of both sites + comparison table]\n\n | Category | myapp.com | stripe.com | Winner |\n | Accessibility | C+ (78) | A (94) | ✅ stripe.com |\n | Performance | B- (81) | A+ (98) | ✅ stripe.com |\n | SEO | D (63) | A (93) | ✅ stripe.com |\n | Overall | C (74) | A (95) | ✅ stripe.com |\n```\n\n### SEO Audit\n```\nYou: Run an SEO audit on https://myapp.com\n\nClaude: [Calls seo_audit]\n [Checks 18 SEO signals: meta tags, Open Graph, structured data, etc.]\n [Returns score, passing checks, and failed checks with fix recommendations]\n [Weighted by impact: critical > high > medium > low]\n```\n\n### Debug Page Load Issues\n```\nYou: What console errors does localhost:3000 produce?\n\nClaude: [Calls capture_console]\n [Returns all console messages + uncaught exceptions]\n\nYou: Show me all network requests on page load\n\nClaude: [Calls capture_network]\n [Returns every request: URL, status, size, timing]\n [Summary grouped by resource type]\n```\n\n### Before/After Comparison\n```\nYou: Compare localhost:3000 with localhost:3001\n\nClaude: [Calls compare_screenshots]\n [Pixel-level diff with red-highlighted changes]\n [Reports exact pixel difference %]\n```\n\n### Semantic Visual Review\n```\nYou: I changed the header to be sticky. Compare before and after.\n\nClaude: [Calls semantic_compare with change description]\n [Captures both states + pixel diff]\n [Evaluates whether changes match the intent]\n [Checks for visual regressions]\n```\n\n### Enforce Performance Budgets\n```\nYou: Check if my site meets our performance budgets\n\nClaude: [Calls check_budgets]\n [Reads thresholds from .uimaxrc.json]\n [Returns ✅ pass or ❌ fail for each metric]\n```\n\n### Generate Shareable Report\n```\nYou: Export a full report of localhost:3000 to ./report.html\n\nClaude: [Calls export_report]\n [Generates standalone dark-themed HTML report]\n [Open in any browser, share with team]\n```\n\n### Multi-Page Audit\n```\nYou: Crawl localhost:3000 and audit all pages\n\nClaude: [Calls crawl_and_review]\n [Discovers internal links, audits up to 10 pages]\n [Per-page: screenshot + accessibility + performance]\n```\n\n---\n\n## What Claude Reviews\n\nWhen using the full `review_ui` pipeline, Claude evaluates:\n\n| Category | What's Checked |\n|----------|----------------|\n| **Visual Design** | Layout, typography, color contrast, whitespace, shadows, icon consistency |\n| **User Experience** | Navigation, interaction states, loading/error/empty states, edge cases |\n| **Accessibility** | WCAG 2.1 AA, keyboard nav, screen reader compat, focus management |\n| **Performance** | Lighthouse scores, Core Web Vitals, render-blocking resources, bundle size |\n| **SEO** | Meta tags, Open Graph, Twitter cards, structured data, heading hierarchy, canonical URLs, image alt text |\n| **Code Quality** | Component architecture, CSS organization, error boundaries, TypeScript safety |\n| **Security** | HTTPS, CSP, vulnerable libraries, mixed content |\n| **Report Card** | Per-section letter grades (A+ through F) for Accessibility, Performance, Best Practices, SEO, Code Quality |\n| **Creative** | Modern UI patterns (Linear, Vercel, Raycast), micro-interactions, animations |\n\n---\n\n## Code Analysis Rules\n\nThe `analyze_code` tool checks for **25+ rules** across categories:\n\n| Rule | Severity | Category |\n|------|----------|----------|\n| `img-no-alt` | High | Accessibility |\n| `click-no-keyboard` | High | Accessibility |\n| `no-form-label` | High | Accessibility |\n| `missing-viewport-meta` | High | Accessibility |\n| `no-lang-attr` | Medium | Accessibility |\n| `no-focus-visible` | Medium | Accessibility |\n| `empty-catch` | High | Code Quality |\n| `react-hooks-conditional` | High | Code Quality |\n| `missing-key-prop` | High | Bug |\n| `console-log` | Low | Code Quality |\n| `todo-fixme` | Low | Code Quality |\n| `inline-style` | Medium | Code Quality |\n| `any-type` | Medium | Code Quality |\n| `magic-number` | Low | Code Quality |\n| `direct-dom-access` | Medium | Code Quality |\n| `event-handler-inline` | Low | Code Quality |\n| `important-css` | Medium | Design |\n| `hardcoded-color` | Low | Design |\n| `z-index-high` | Medium | Design |\n| `font-too-small` | Medium | Design |\n| `no-lazy-image` | Medium | Performance |\n| `large-bundle-import` | Medium | Performance |\n| `no-error-boundary` | Medium | UX |\n| `missing-meta-description` | Medium | UX |\n| `large-file` | Medium/High | Code Quality |\n| `deep-nesting` | Medium/High | Code Quality |\n\nAll rules can be toggled via [`.uimaxrc.json`](#configuration).\n\n---\n\n## Supported Frameworks\n\nAuto-detected from `package.json`:\n- React / Next.js\n- Vue / Nuxt\n- Svelte / SvelteKit\n- Angular\n- Plain HTML/CSS/JS\n\n---\n\n## Requirements\n\n- **Node.js** >= 18.0.0\n- **Chrome/Chromium** (uses your system Chrome — no extra download)\n- **Claude Code** (for MCP integration)\n- **No API keys needed** — runs entirely within Claude Code using your existing Pro plan\n\n---\n\n## How It Works\n\n```\n+----------------------------------------------------------------------+\n| Claude Code (your Pro plan) |\n| |\n| User: \"Review my UI at localhost:3000 and fix everything\" |\n| | |\n| v |\n| +----------------------------------------------------------------+ |\n| | UIMax MCP (37 tools) | |\n| | | |\n| | Screenshot -------> Puppeteer ----------> PNG Image | |\n| | Accessibility ----> axe-core ------------> WCAG Violations | |\n| | Lighthouse -------> Google LH ----------> Scores + Audits | |\n| | Deep LH ----------> PWA/Security/LCP --> Granular Analysis | |\n| | SEO Audit --------> 18 checks ----------> SEO Score | |\n| | Performance ------> Perf API ----------> Web Vitals | |\n| | Code Scan --------> TypeScript AST -----> Anti-patterns | |\n| | Report Card ------> Grading Engine -----> A+ to F Grades | |\n| | Browser ----------> Click/Type/Scroll --> Interaction | |\n| | Debugging --------> Console/Network ----> Runtime Data | |\n| | History ----------> .uimax-reviews.json > Progress Tracking | |\n| | Expert Prompt ----> Baked-in methodology | |\n| +----------------------------+-----------------------------------+ |\n| | |\n| v |\n| Claude Code receives: screenshot + data + expert methodology |\n| | |\n| v |\n| Claude acts as world-class frontend expert (FREE -- Pro plan) |\n| Generates comprehensive review with exact fixes |\n| | |\n| v |\n| Claude implements every fix in the codebase automatically |\n| |\n+----------------------------------------------------------------------+\n```\n\n---\n\n## CI / GitHub Action\n\nUIMax ships with a reusable GitHub Action that runs audits on every PR and posts a Report Card comment.\n\n### Quick Setup\n\nCopy the example workflow to your project:\n\n```yaml\n# .github/workflows/uimax-ci.yml\nname: UIMax Review\non:\n pull_request:\n branches: [main]\n\njobs:\n uimax-review:\n runs-on: ubuntu-latest\n steps:\n - uses: actions/checkout@v4\n - uses: actions/setup-node@v4\n with:\n node-version: \"20\"\n\n # Build and start your app\n - run: npm ci && npm run build\n - run: npm start &\n - run: npx wait-on http://localhost:3000\n\n # Run UIMax\n - uses: prembobby39-gif/uimax-mcp/.github/actions/uimax-review@main\n with:\n url: http://localhost:3000\n budget-accessibility: 90\n budget-performance: 80\n budget-seo: 80\n max-violations: 0\n```\n\n### Action Inputs\n\n| Input | Description | Required | Default |\n|-------|-------------|----------|---------|\n| `url` | URL to audit | Yes | — |\n| `github-token` | Token for PR comments | No | `GITHUB_TOKEN` |\n| `budget-performance` | Min performance score (0-100) | No | — |\n| `budget-accessibility` | Min accessibility score (0-100) | No | — |\n| `budget-seo` | Min SEO score (0-100) | No | — |\n| `max-violations` | Max allowed a11y violations | No | — |\n| `fail-on-regression` | Fail if grades regress | No | `false` |\n\n### Action Outputs\n\n| Output | Description |\n|--------|-------------|\n| `accessibility-grade` | Letter grade (A+ through F) |\n| `performance-grade` | Letter grade |\n| `seo-grade` | Letter grade |\n| `total-violations` | Accessibility violation count |\n| `passed` | Whether all budgets passed (`true`/`false`) |\n| `report` | Full markdown report |\n\nThe action updates existing UIMax comments on re-push (no duplicate comments).\n\nSee `examples/uimax-ci.yml` for a complete working example.\n\n---\n\n## Development\n\n```bash\n# Clone\ngit clone https://github.com/prembobby39-gif/uimax-mcp.git\ncd uimax-mcp\n\n# Install\nnpm install\n\n# Build\nnpm run build\n\n# Run tests\nnpm test\n\n# Run tests with coverage\nnpm run test:coverage\n\n# Test locally with Claude Code\nclaude mcp add uimax-dev -- node /path/to/uimax-mcp/dist/index.js\n```\n\n---\n\n## Contributing\n\nContributions welcome! Some ideas:\n\n- [ ] CSS specificity analyzer\n- [ ] Design token extraction\n- [ ] Framework-specific checks (Vue composition API, Svelte stores)\n- [x] Visual regression with pixel-level diffing\n- [x] Performance budgets (fail if scores drop below thresholds)\n- [x] Browser interaction (click, type, scroll, navigate)\n- [x] Console and network capture\n- [x] Deep Lighthouse analysis (PWA, security, unused code, LCP, resources)\n- [x] AI-powered semantic visual comparison\n- [x] Review history tracking with auto-save\n- [x] Dedicated SEO audit (18 checks, weighted scoring)\n- [x] Per-section letter grades (A+ through F Report Card)\n- [x] Verify fixes (before/after comparison with grade transitions)\n- [x] Competitive benchmarking (side-by-side site comparison)\n- [x] CI/CD integration (GitHub Action for automated review on PR)\n- [ ] Custom rule plugins (user-defined regex rules)\n- [ ] Figma design comparison (screenshot vs Figma mock)\n- [ ] Cross-browser testing (Firefox, WebKit via Playwright)\n\n---\n\n## License\n\nMIT\n", "bytes": 25901, "sha": "0032d0d5d5f28cf36b15d82d2443acb2061f699ea7cb7de1d32f8da2196f8b81", "repo_slug": "prembobby39-gif/uimax-mcp", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_prembobby39_gif_uimax_mcp_0f92dc51/readme" }