Accessibility Prover MCP Connector for Claude
A+Accessibility Prover is a pre-build validation system that forces WCAG 2.2 AA compliance before code is written. It audits semantic HTML, keyboard navigation, contrast ratios (4.5:1 minimum), screen reader compatibility, and motion safety across 5 structured Decision Pivots. Unlike runtime scanners, it catches div soup, missing focus traps, and inaccessible animations during the design phase — before they reach production and before they violate the European Accessibility Act (EAA 2025).
Accessibility Prover validates user interface specifications against WCAG 2.2 AA standards using structured reasoning — not DOM scanning. It acts as a pre-build gate that forces AI agents and front-end developers to satisfy accessibility rules before writing component code.
The Problem It Solves
Five accessibility barriers account for 92% of the issues flagged by the WebAIM Million annual report:
- Div soup — Replacing semantic tags (
,,,) with nestedstructures, rendering the interface invisible to assistive technology. Screen readers cannot infer the role of a— it is functionally absent. - Keyboard trapped — Leaving interactive elements unreachable by keyboard navigation, removing visible focus indicators, or failing to trap focus inside active modals. 2.5 million keyboard-only users in the EU cannot use a button they cannot reach.
- Contrast failing — Using color combinations below the WCAG 2.2 AA 4.5:1 minimum ratio (3:1 for large text). A contrast ratio of 2.1:1 means 1 in 12 men with color vision deficiency cannot read the label.
- Screen reader blind — Omitting image alt texts, aria-labels on icon buttons, or form-label associations. An unlabeled `` with an SVG icon is announced as "button" with no context — the user does not know what it does.
- Motion hostile — Animations without
prefers-reduced-motionmedia queries trigger vestibular disorders affecting 35% of adults over 40. Auto-playing carousels and parallax scrolling are the most common offenders.
How It Works
Accessibility Prover validates UI specifications using 5 Decision Pivots. Each pivot produces one of six structured verdicts: A11Y_PROVEN, DIV_SOUP, KEYBOARD_TRAPPED, CONTRAST_FAILING, SCREEN_READER_BLIND, or MOTION_HOSTILE.
- semanticHTML — Are correct HTML5 elements used for their intended purpose?
for actions,for navigation,for form fields. Customor `` elements with click handlers are rejected. - keyboardNavigable — Is there a logical tab order? Are focus indicators visible (
:focus-visible)? Do modals and dialogs implement focus traps? Can the user escape every interactive region? - contrastCompliant — Do foreground/background color combinations satisfy the 4.5:1 ratio across default, hover, focus, active, and disabled states? Large text (18px+ or 14px+ bold) allows 3:1.
- screenReaderReady — Are images described (
alt), icon buttons labeled (aria-label), form fields associated (``), and decorative elements hidden (aria-hidden="true")? - motionRespected — Are animations wrapped in
@media (prefers-reduced-motion: no-preference)? Do transitions respect duration limits? Is auto-play disabled by default?
Why It Works
- Shift-left compliance. Fixing a contrast ratio during design takes 2 minutes. Fixing it after a production accessibility audit takes 2 sprints — plus the legal review, the backlog reprioritization, and the release cycle.
- EAA 2025 enforcement. Since June 2025, the European Accessibility Act applies to all digital products sold in the EU. Non-compliance carries fines up to 5% of annual revenue. Accessibility Prover creates an auditable pre-build record that demonstrates due diligence.
- AI agent guardrail. When AI coding agents generate front-end code, they default to div-based layouts with decorative styling. Accessibility Prover intercepts the specification and forces semantic HTML, ARIA attributes, and contrast verification before the code is written.
Related Connectors
Deadline Calculator MCP
Calculate precise end dates by adding calendar or business days, accounting for weekends and regional holidays.
Dog Body Language Decoder MCP
Interprets dog body signals (posture, ears, tail, face) to determine emotional state and provides actionable safety guidelines for safe human interaction.
Stud Wall Load Calculator MCP
Calculate the allowable axial and lateral load capacity for wood stud walls based on NDS standards.
Fill Rate Calculator MCP
Calculate Order, Line, and Unit Fill Rate metrics along with stockout costs.