Accessibility MCP for AI Agents – Automate WCAG Compliance
Let Cursor, Claude Code, and VS Code scan and fix web accessibility directly in your IDE – WCAG 2.1 Level AA compliant, without context switching and without manual audits.
Works with Cursor, VS Code & Claude Code
Accessibility Compliance Is Hard. Missing Deadlines Is Expensive.
Since June 2025, the German Accessibility Strengthening Act (BFSG) requires digital services to meet WCAG 2.1 Level AA — with fines up to €100,000 for non-compliance. The European Accessibility Act extends similar requirements across the EU.
Manual audits are slow, expensive, and happen too late. By the time your team finds issues in production, the cost to fix them has multiplied.
What if your developers could catch and fix accessibility issues while they code?
Three Steps to Accessible Code
Your agent scans the page in a real browser
The AI agent opens your localhost page in headless Chromium, runs axe-core against WCAG 2.1 Level A + AA rules, and returns a structured report — all within your IDE.
"Scan http://localhost:3000 for accessibility issues"A prioritized fix plan is generated automatically
Violations are mapped to WCAG success criteria and EN 301 549 clauses, sorted by severity (critical → minor), and written to a structured plan file your agent can execute.
→ 3 critical · 5 serious · 2 moderate
→ .navable-plan.json written to project rootYour agent applies fixes using proven code patterns
The agent works through each item, loads the right fix guide, applies the code change, and marks it done. Re-scan to verify. All tracked in one plan file.
✓ fix-1 image-alt done
✓ fix-2 color-contrast done
✓ fix-3 label done
○ fix-4 heading-order pendingTwo Tools. One Workflow.
The MCP server provides the scanning engine. The agent skills provide structured, step-by-step instructions. Together, your AI agent follows a deterministic, repeatable workflow — not improvisation.
@navable/mcpThe engine behind automated accessibility scanning. Connects your AI coding agent to a real Chromium browser running axe-core — the industry standard for accessibility testing. New in v0.2: opt-in dual-engine scanning with Pa11y/HTMLCS for cross-confirmed findings.
- Scans any localhost URL in a real browser (Playwright + axe-core)
- Optional dual-engine scanning with Pa11y/HTMLCS (v0.2) — cross-confirmed findings for audit-grade confidence
- Returns WCAG 2.1 Level A + AA violations with severity, affected elements, and fix hints
- Maps every finding to EN 301 549 clauses (EU/BFSG compliance)
- Generates structured fix plans your agent can execute step by step
- Tracks fix progress — mark items done, skipped, or in progress
- Ships 8 built-in reference resources: WCAG mapping, ARIA patterns, semantic HTML, fix patterns
Works with:
Without skills, your agent improvises. With them, it follows a structured, repeatable playbook: scan → plan → fix → verify. Drop them into your project and every accessibility workflow runs the same way, every time.
Scan & Fix
Scans a URL → generates a fix plan → applies code fixes → verifies with a re-scan
Fix Plan Executor
Resumes an existing fix plan and works through remaining items
Component Review
Reviews source code for accessibility issues — no browser needed, perfect for PR reviews
Page Structure Audit
Audits landmarks, heading hierarchy, navigation patterns, and document metadata
10 fix guides included:
Images, Forms, Color & Contrast, Navigation, Headings, Landmarks, ARIA, Keyboard, Language, Tables
Works with:
Built-In Accessibility Knowledge
Your agent doesn't guess — it references industry standards loaded on-demand to keep responses fast and accurate.
All 50 Level A + AA success criteria mapped to EN 301 549 clauses, with testability classification and axe-core rule IDs.
25 WAI-ARIA widget patterns from the W3C APG — roles, attributes, keyboard interactions, focus management, and common mistakes.
Reference of HTML elements with implicit ARIA roles, correct usage patterns, and the mistakes developers make most often.
55 axe-core rules with concrete before/after code examples, framework notes for React and Vue, and WCAG criteria references.
Built for BFSG & European Accessibility Act Compliance
The Barrierefreiheitsstärkungsgesetz (BFSG) has been in force since June 2025. E-commerce, banking, transport, and digital services must meet WCAG 2.1 Level AA — backed by the harmonised standard EN 301 549.
navable tools map scan findings to the respective EN 301 549 clauses, so your compliance documentation writes itself as your developers fix issues.
- WCAG 2.1 Level A + AA (50 success criteria)
- EN 301 549 v3.2.1 clause mapping
- BFSG scope coverage (e-commerce, banking, transport, media)
- Automated + semi-automated testability classification
- Fix tracking with timestamps for audit trail
- WCAG 2.2 forward-looking recommendations included
Get Started in Under 2 Minutes
Add one config file to your project. The MCP server installs automatically via npx. Chromium downloads on first run. No API keys. No accounts. Free forever.
Create .vscode/mcp.json:
{
"servers": {
"navable": {
"command": "npx",
"args": ["-y", "@navable/mcp"]
}
}
}After setup, ask your agent:
"Scan http://localhost:3000 for accessibility issues"That's it. The agent handles the rest.
Watch: Scan, Plan & Fix in Under 2 Minutes
A real scan of a localhost page — from prompt to prioritized fix plan.
Frequently Asked Questions
Start Shipping Accessible Products Today
Free. Open source. Set up in 2 minutes. No excuses.