vertaaux-mcp
Enables AI agents to open draft GitHub PRs with framework-aware patches applied atomically via Git Trees API, and export audit results as SARIF for GitHub Code Scanning.
Provides semantic markup auditing capabilities including HTML5 validation, heading hierarchy analysis, and landmark region assessment as part of UX audits.
Supports static analysis of JavaScript codebases for UX and accessibility issues, with framework-aware patch generation for detected problems.
Supports auditing from Lighthouse JSON artifacts as input sources for comprehensive UX and accessibility analysis alongside other audit engines.
Provides npm package distribution and installation options for the MCP server, enabling easy deployment and integration into development workflows.
Supports framework-aware patch generation for React codebases, automatically detecting React components and generating appropriate fixes for UX and accessibility issues.
Supports framework-aware patch generation for Svelte codebases, automatically detecting Svelte components and generating appropriate fixes for UX and accessibility issues.
Includes SVG analysis as part of accessibility audits, checking for proper ARIA usage and accessibility attributes in SVG elements.
VertaaUX MCP Server
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.
Why this server is different
verify_fixesloop: close the audit, fix, re-audit cycle without leaving the agent loop. Budget-capped at 3 iterations to prevent runaway billing.Framework-aware patches:
suggest_fixdetects React/Vue/Angular/Svelte/Nuxt via the nearestpackage.jsonand emits idiomatic patches (JSX rewrites for React, HTML attrs preserved elsewhere).Atomic Git Trees PRs:
generate_prapplies 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.Deterministic finding IDs:
rule:hashformat stable across audit runs so agents can reference findings without storing state.Multi-engine a11y:
audit_a11ycombines axe-core, AccessLint, and VertaaUX analyzers in a single call.Policy-as-code:
policy_checkmirrors the GitHub Action's threshold evaluator exactly so CI and agent verdicts match.
Features
38 Tools across audit, fix, PR, schedule, webhook, policy, and a11y categories
7 Prompt Templates for common workflows
8 Resource URIs for audit data and UX guidelines
Enterprise Controls: domain allowlist, rate limiting, PII redaction
Dual Transport: stdio (CLI/Desktop) + HTTP streaming (web)
Official MCP SDK: spec-compliant via
@modelcontextprotocol/sdk
Install
MCP Official Registry
npx -y @modelcontextprotocol/cli install io.github.PetriLahdelma/vertaaux-mcpnpm
npm install -g @vertaaux/mcp-server
VERTAAUX_API_KEY=vx_live_... vertaaux-mcpDrift 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.
Quick Start
# Install & build
npm install && npm run build
# Run (stdio transport, for Claude Desktop, VS Code, Cursor)
VERTAAUX_API_KEY=vx_live_... npm start
# Run (HTTP transport, for web clients)
VERTAAUX_API_KEY=vx_live_... npm run start:httpIDE Integration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"vertaaux": {
"command": "node",
"args": ["/path/to/mcp-server/dist/index.js"],
"env": {
"VERTAAUX_API_KEY": "vx_live_..."
}
}
}
}VS Code (with MCP extension)
Add to .vscode/settings.json:
{
"mcp.servers": {
"vertaaux": {
"command": "node",
"args": ["./mcp-server/dist/index.js"],
"env": {
"VERTAAUX_API_KEY": "vx_live_..."
}
}
}
}Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"vertaaux": {
"command": "node",
"args": ["/path/to/mcp-server/dist/index.js"],
"env": {
"VERTAAUX_API_KEY": "vx_live_..."
}
}
}
}Environment Variables
Variable | Required | Default | Purpose |
| Yes | — | API authentication key |
| No |
| API endpoint URL |
| No |
| HTTP transport port |
| No | — | GitHub API access for |
Tools
Audit Tools (Core)
Tool | Description |
| Run UX & accessibility audit on a deployed URL. Returns top 5 issues with severity breakdown. |
| Static analysis on local codebase (React/Vue/Svelte/HTML). Finds missing alt text, unlabeled buttons/inputs/links. |
| Audit from HAR files (response times, failed requests, large payloads) or Lighthouse JSON (accessibility findings). |
| Retrieve findings from a completed audit with filtering by severity, rule, and pagination. |
| Get audit job status and results by job ID. |
Fix & Verify Tools
Tool | Description |
| Deep-dive into a finding: WCAG criteria, repro steps, fix guidance, before/after code examples. |
| Generate search/replace patch with confidence score. Supports single and batch mode. |
| Generate accessibility fix patch for a specific issue from an audit. |
| Verify a patch fixes the issue without regressions via before/after audit. |
| Create a draft GitHub PR with fix patches. Requires |
| Generate a PR comment with suggestion blocks, ordered by severity. |
Analysis Tools
Tool | Description |
| Heuristic UX review of component code (no browser needed). Checks images, buttons, inputs, links. |
| Provider-agnostic LLM audit (Mistral/OpenAI via Vertaa adapter). |
| Capture screenshot by running a quick audit. |
| Compare UX metrics against competitor URLs with category-level score deltas. |
| Format an issue into developer-friendly markdown guidance. |
Management Tools
Tool | Description |
| Register webhook for audit notifications. |
| Manage webhooks. |
| Cron-based scheduled audits with score threshold alerts. |
| Manage schedules. |
| Check plan and remaining credits. |
| List available engine versions. |
Accessibility Tools (Multi-Engine)
Tool | Description |
| Multi-engine accessibility audit using axe-core, AccessLint, and custom analyzers. Returns WCAG-mapped findings with structured fix suggestions and fixability ratings. Supports |
| Compare current accessibility findings against a saved baseline. Returns fixed, new, and unchanged findings with net change summary. Requires a prior |
Deprecated
Tool | Description |
| DEPRECATED — Use |
Prompt Templates
Pre-built workflow prompts for common audit scenarios:
Prompt | Description | Arguments |
| Audit a URL and summarize top issues with fix recommendations |
|
| Full audit → patch → PR comment workflow |
|
| Compare against competitors and identify UX gaps |
|
| Set up scheduled monitoring with alerts |
|
| Static analysis on local codebase |
|
Resources
The server exposes MCP resources via vertaa:// URIs:
URI Pattern | Description |
| Full audit result |
| Lightweight summary |
| Single finding detail |
| Screenshot metadata |
| Annotated screenshot |
| Audit history for URL |
| Score trend analysis |
| UX guidelines (buttons, forms, navigation, color-contrast, errors, content) |
Enterprise Controls
Configure domain allowlists, rate limits, and PII redaction programmatically:
import { configureEnterpriseControls } from './server.js';
configureEnterpriseControls({
allowlist: {
allowed_domains: ['*.example.com'],
denied_domains: ['internal.example.com'],
},
budget: {
max_requests: 100,
max_pages: 50,
max_duration_ms: 60000,
max_concurrency: 3,
},
redaction: {
redact_emails: true,
redact_phone_numbers: true,
redact_credit_cards: true,
custom_patterns: [
{ name: 'api_key', pattern: 'sk_[a-zA-Z0-9]{20,}', replacement: '[REDACTED]' }
],
},
});Example: Audit-to-PR Workflow
1. audit_url({ url: "https://example.com", mode: "deep" })
→ Returns audit_id with top 5 issues
2. get_findings({ audit_id: "...", severity: "critical" })
→ Returns all critical findings with deterministic IDs
3. suggest_fix({ audit_id: "...", finding_id: "button-name:a1b2c3d4" })
→ Returns search/replace patch with 85% confidence
4. run_verification_suite({ url: "...", selector: "button.submit", rule_id: "button-name" })
→ Verifies fix resolves the issue
5. create_pr_comment({ file_path: "src/Button.tsx", patches: [...] })
→ Generates PR comment with suggestion blocksDevelopment
Project Structure
mcp-server/
├── src/
│ ├── index.ts # Main entry, tool registration
│ ├── server.ts # MCP server config, resources, middleware
│ ├── a11y-tools.ts # Multi-engine a11y audit & baseline diffing tools
│ ├── http.ts # HTTP transport entry point
│ ├── prompts.ts # MCP prompt templates
│ ├── analysis.ts # Component analysis engine
│ ├── patch.ts # Patch generation
│ ├── verification.ts # Patch verification
│ ├── pr-comment.ts # PR comment generation
│ ├── tools/
│ │ ├── audit-url.ts # audit_url tool
│ │ ├── audit-repo.ts # audit_repo tool (static analysis)
│ │ ├── audit-artifact.ts # audit_artifact tool (HAR/Lighthouse)
│ │ ├── get-findings.ts # get_findings tool
│ │ ├── explain-finding.ts# explain_finding tool
│ │ ├── suggest-fix.ts # suggest_fix tool
│ │ ├── generate-pr.ts # generate_pr tool
│ │ └── index.ts # Tool exports
│ ├── transports/
│ │ ├── stdio.ts # Stdio transport (default)
│ │ └── http.ts # HTTP streaming transport
│ ├── middleware/
│ │ ├── allowlist.ts # Domain/path allowlist
│ │ ├── budget.ts # Rate limiting & quotas
│ │ ├── redaction.ts # PII redaction
│ │ └── index.ts # Middleware stack
│ ├── resources/
│ │ ├── audit-results.ts # vertaa://audits/* resources
│ │ ├── screenshots.ts # vertaa://screenshots/* resources
│ │ ├── historical.ts # vertaa://history/* resources
│ │ ├── legacy.ts # Guidelines resources
│ │ └── index.ts # Resource exports
│ ├── schemas/
│ │ ├── audit.ts # Audit schemas (mode, findings)
│ │ ├── findings.ts # Finding schemas
│ │ ├── controls.ts # Enterprise control schemas
│ │ ├── errors.ts # Error schemas
│ │ └── index.ts
│ ├── utils/
│ │ ├── error-recovery.ts # Structured errors with recovery guidance
│ │ ├── change-tracker.ts # Baseline change tracking
│ │ └── deterministic-id.ts # Stable finding IDs
│ └── index.test.ts # Test suite
├── README.md
├── package.json
├── tsconfig.json
└── vitest.config.tsTesting
npm test # Run test suite
npm run test:watch # Watch mode
npm run test:coverage # Coverage reportBuilding
npm run build # TypeScript → dist/Error Handling
All errors include structured recovery guidance:
{
"code": "AUDIT_NOT_FOUND",
"message": "Audit abc123 not found.",
"recovery": {
"action": "Start a new audit for this URL",
"tool": "audit_url",
"params": { "url": "https://example.com" }
}
}Error codes follow JSON-RPC 2.0: -32700 (parse), -32600 (invalid request), -32601 (method not found), -32602 (invalid params), -32603 (internal error).
API Reference
The MCP server communicates with the VertaaUX API v1. See the API Documentation.
License
MIT
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/VertaaUX/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server