Autonomous UX and a11y audit, fix, and verify loop. 38 tools, framework-aware patches.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
The only MCP server with an autonomous audit, fix, and verify loop. Detects UX and accessibility issues across 7 categories, generates framework-aware patches (React, Vue, Angular, Svelte), opens atomic GitHub PRs via the Git Trees API, and verifies the fix landed in production. Built for CI/CD pipelines with policy-as-code thresholds.
verify_fixes loop: close the audit, fix, re-audit cycle without leaving the agent loop. Budget-capped at 3 iterations to prevent runaway billing.suggest_fix detects React/Vue/Angular/Svelte/Nuxt via the nearest package.json and emits idiomatic patches (JSX rewrites for React, HTML attrs preserved elsewhere).generate_pr applies N patches in a single commit or zero. Conflict graph + AST gate (Babel, vue-eslint-parser, svelte/compiler) refuse unparseable patches before they reach the PR.rule:hash format stable across audit runs so agents can reference findings without storing state.audit_a11y combines axe-core, AccessLint, and VertaaUX analyzers in a single call.policy_check mirrors the GitHub Action's threshold evaluator exactly so CI and agent verdicts match.@modelcontextprotocol/sdkDrift policy:
smithery.yaml,glama.json, andserver.jsonare auto-generated from the live MCP tool registry bynpm run generate:manifests. Never hand-edit them. Seedocs/REGISTRY-PUBLISHING.mdfor the runbook.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
Add to .vscode/settings.json:
Add to .cursor/mcp.json:
| Variable | Required | Default | Purpose |
|---|---|---|---|
VERTAAUX_API_KEY | Yes | β | API authentication key |
VERTAAUX_API_BASE | No | https://vertaaux.ai/api/v1 | API endpoint URL |
PORT | No | 8787 | HTTP transport port |
GITHUB_TOKEN | No | β | GitHub API access for generate_pr |
| Tool | Description |
|---|---|
audit_url | Run UX & accessibility audit on a deployed URL. Returns top 5 issues with severity breakdown. |
audit_repo | Static analysis on local codebase (React/Vue/Svelte/HTML). Finds missing alt text, unlabeled buttons/inputs/links. |
audit_artifact | Audit from HAR files (response times, failed requests, large payloads) or Lighthouse JSON (accessibility findings). |
get_findings | Retrieve findings from a completed audit with filtering by severity, rule, and pagination. |
get_audit | Get audit job status and results by job ID. |
| Tool | Description |
|---|---|
explain_finding | Deep-dive into a finding: WCAG criteria, repro steps, fix guidance, before/after code examples. |
suggest_fix | Generate search/replace patch with confidence score. Supports single and batch mode. |
generate_patch | Generate accessibility fix patch for a specific issue from an audit. |
run_verification_suite | Verify a patch fixes the issue without regressions via before/after audit. |
generate_pr | Create a draft GitHub PR with fix patches. Requires GITHUB_TOKEN. |
create_pr_comment | Generate a PR comment with suggestion blocks, ordered by severity. |
| Tool | Description |
|---|---|
analyze_component | Heuristic UX review of component code (no browser needed). Checks images, buttons, inputs, links. |
run_llm_audit | Provider-agnostic LLM audit (Mistral/OpenAI via Vertaa adapter). |
capture_screenshot | Capture screenshot by running a quick audit. |
compare_competitors | Compare UX metrics against competitor URLs with category-level score deltas. |
explain_issue | Format an issue into developer-friendly markdown guidance. |
| Tool | Description |
|---|---|
create_webhook | Register webhook for audit notifications. |
list_webhooks / delete_webhook | Manage webhooks. |
create_schedule | Cron-based scheduled audits with score threshold alerts. |
get_schedule / list_schedules / update_schedule / delete_schedule | Manage schedules. |
get_quota | Check plan and remaining credits. |
get_engines | List available engine versions. |
| Tool | Description |
|---|---|
audit_a11y | Multi-engine accessibility audit using axe-core, AccessLint, and custom analyzers. Returns WCAG-mapped findings with structured fix suggestions and fixability ratings. Supports min_impact filtering and mode (basic/standard/deep). |
diff_a11y | Compare current accessibility findings against a saved baseline. Returns fixed, new, and unchanged findings with net change summary. Requires a prior audit_a11y call to establish the baseline. |
| Tool | Description |
|---|---|
run_audit | DEPRECATED β Use audit_url instead. |
Pre-built workflow prompts for common audit scenarios:
| Prompt | Description | Arguments |
|---|---|---|
quick_audit | Audit a URL and summarize top issues with fix recommendations | url |
fix_accessibility | Full audit β patch β PR comment workflow | url |
compare_ux | Compare against competitors and identify UX gaps | url, competitors, industry? |
monitor_regression | Set up scheduled monitoring with alerts | url, frequency? |
audit_codebase | Static analysis on local codebase | path |
The server exposes MCP resources via vertaa:// URIs:
| URI Pattern | Description |
|---|---|
vertaa://audits/{auditId} | Full audit result |
vertaa://audits/{auditId}/summary | Lightweight summary |
vertaa://audits/{auditId}/findings/{findingId} | Single finding detail |
vertaa://screenshots/{auditId} | Screenshot metadata |
vertaa://screenshots/{auditId}/annotated | Annotated screenshot |
vertaa://history/{encodedUrl} | Audit history for URL |
vertaa://history/{encodedUrl}/trend | Score trend analysis |
vertaa://guidelines/{topic} | UX guidelines (buttons, forms, navigation, color-contrast, errors, content) |
Configure domain allowlists, rate limits, and PII redaction programmatically:
All errors include structured recovery guidance:
Error codes follow JSON-RPC 2.0: -32700 (parse), -32600 (invalid request), -32601 (method not found), -32602 (invalid params), -32603 (internal error).
The MCP server communicates with the VertaaUX API v1. See the API Documentation.
MIT
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/vertaaux-mcp-2)<a href="https://allmcps.com/mcp/vertaaux-mcp-2"><img src="https://allmcps.com/api/badge/vertaaux-mcp-2?style=directory" alt="Vertaaux Mcp on AllMCPs" /></a>