vertaaux-mcp
MCP server for VertaaUX.ai — run UX & accessibility audits, generate fixes, and monitor quality from your LLM or IDE. 38 tools covering the full audit-to-fix lifecycle across 7 UX categories.
README
<div align="center">
<img src="banner-light.svg#gh-light-mode-only" alt="VERTAAUX" width="600" /> <img src="banner-dark.svg#gh-dark-mode-only" alt="VERTAAUX" width="600" />
MCP server for VertaaUX.ai — run UX & accessibility audits, generate fixes, and monitor quality from your LLM or IDE.
</div>
This server exposes 38 tools via the Model Context Protocol so AI coding agents can audit live URLs, explain findings, generate framework-aware patches, and open draft PRs — all without leaving the conversation.
Quick Start
MCP Official Registry
npx -y @modelcontextprotocol/cli install io.github.PetriLahdelma/vertaaux-mcp
npm
npm install -g @vertaaux/mcp-server
VERTAAUX_API_KEY=vx_live_... vertaaux-mcp
npx (zero install)
VERTAAUX_API_KEY=vx_live_... npx -y @vertaaux/mcp-server
Get your API key at vertaaux.ai/settings/api.
IDE Integration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"vertaaux": {
"command": "npx",
"args": ["-y", "@vertaaux/mcp-server"],
"env": {
"VERTAAUX_API_KEY": "vx_live_..."
}
}
}
}
VS Code
Add to .vscode/settings.json:
{
"mcp.servers": {
"vertaaux": {
"command": "npx",
"args": ["-y", "@vertaaux/mcp-server"],
"env": {
"VERTAAUX_API_KEY": "vx_live_..."
}
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"vertaaux": {
"command": "npx",
"args": ["-y", "@vertaaux/mcp-server"],
"env": {
"VERTAAUX_API_KEY": "vx_live_..."
}
}
}
}
What Your Agent Can Do
Once connected, your AI agent gains access to 38 tools across the full audit-to-fix lifecycle:
Audit
| Tool | Description |
|---|---|
audit_url |
Run UX & accessibility audit on a deployed URL |
audit_repo |
Static analysis on local codebase (React/Vue/Svelte/HTML) |
audit_artifact |
Audit from HAR files or Lighthouse JSON |
audit_a11y |
Multi-engine accessibility audit (axe-core + AccessLint + custom) |
compare_competitors |
Side-by-side UX metrics against competitor URLs |
capture_screenshot |
Capture annotated screenshot of a URL |
Fix
| Tool | Description |
|---|---|
explain_finding |
Deep-dive: WCAG criteria, repro steps, before/after code |
suggest_fix |
Framework-aware search/replace patch with confidence score |
generate_pr |
Open a draft GitHub PR with patches applied atomically |
run_verification_suite |
Verify a patch resolves the issue before committing |
Monitor
| Tool | Description |
|---|---|
diff_audits |
Compare two audits — fixed, broken, and regressed findings |
verify_fixes |
Post-deploy verification against a baseline |
create_schedule |
Cron-based recurring audits with score alerts |
policy_check |
Evaluate audit against vertaa.policy.yml thresholds |
Manage
| Tool | Description |
|---|---|
get_findings |
Paginated findings with severity/rule filtering |
triage_finding |
Set triage state (open/in_progress/resolved/wont_fix) |
create_webhook |
Register webhooks for audit event notifications |
get_quota |
Check remaining credits and tier |
generate_sarif |
Export audit as SARIF 2.1.0 for GitHub Code Scanning |
Workflow Example
1. audit_url({ url: "https://staging.myapp.com", mode: "deep" })
→ Returns scored findings across 7 UX categories
2. suggest_fix({ audit_id: "...", finding_id: "button-name:a1b2c3d4" })
→ Framework-aware patch (React/Vue/Svelte detected automatically)
3. generate_pr({ patches: [...], repo: "owner/repo", branch: "fix/a11y" })
→ Draft PR with patches applied atomically via Git Trees API
4. verify_fixes({ url: "...", baseline_audit_id: "..." })
→ Confirms fixes landed in production
Scoring Categories
Every audit scores across seven weighted categories:
| Category | Weight | What it measures |
|---|---|---|
| Accessibility | 20% | WCAG compliance, ARIA usage, color contrast |
| Conversion | 20% | CTA clarity, form UX, trust signals |
| Usability | 20% | Navigation, cognitive load, responsiveness |
| Clarity | 15% | Value proposition, scanability, messaging |
| Information Architecture | 10% | Navigation depth, grouping, consistency |
| Semantic Markup | 8% | Heading hierarchy, landmark regions, HTML5 |
| Keyboard Navigation | 7% | Focus order, tab traps, skip links |
Environment Variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
VERTAAUX_API_KEY |
Yes | — | API authentication key |
VERTAAUX_API_BASE |
No | https://vertaaux.ai/api/v1 |
API endpoint URL |
PORT |
No | 8787 |
HTTP transport port |
GITHUB_TOKEN |
No | — | GitHub API access for generate_pr |
Prompt Templates
Pre-built workflow prompts for common scenarios:
| Prompt | Description |
|---|---|
quick_audit |
Audit a URL and summarize top issues with fix recommendations |
fix_accessibility |
Full audit → patch → PR comment workflow |
compare_ux |
Compare against competitors and identify UX gaps |
monitor_regression |
Set up scheduled monitoring with alerts |
audit_codebase |
Static analysis on local codebase |
Resources
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://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) |
Related
- @vertaaux/cli — CLI for terminal and CI/CD workflows
- @vertaaux/sdk — JavaScript SDK
- VertaaUX Agent Skills — Agent Skills for Claude Code, Codex, Cursor, and more
- vertaaux.ai — Web dashboard
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.