kinti/a11y-toolkit

26 MCP tools, 6 prompts and a skill covering the whole WCAG 2.2 loop: audit, fix,
document, watch, hand off — and now blindfold usability testing, where the agent
attempts real tasks perceiving only what a screen reader exposes. 51 of 55 A/AA criteria carry automated signals (93%), every
finding ships with a concrete remediation your agent can apply, and the rendered tools
run on whichever browser you have — Chromium, Firefox, WebKit, Chrome or Edge.
The European Accessibility Act is in force since June 2025, ADA suits keep landing,
and AI agents now write most of the web. A scan is not a defence: the machine finds,
the human signs.
What no other a11y tool gives an agent
| Capability | axe-core / Lighthouse / pa11y | a11y-toolkit |
|---|---|---|
| Text contrast over images and gradients (pixel sampling of the real background) | ✗ | ✓ |
| VPAT 2.5 (WCAG) draft from the evidence pack — US/ADA counterpart of the EAA statement | ✗ | ✓ |
| Form error testing: fills invalid data, really submits, judges what happens | ✗ | ✓ |
| Keyboard traps: real Tab walk + Escape-release test, plus focus/input-triggered navigation | ✗ | ✓ |
| Infinite-scroll audit: focus survival, announcements, feed end | ✗ | ✓ |
| Reflow at 320px and the WCAG text-spacing override, measured | ✗ | ✓ |
| Screen reader transcript: what a blind user hears, linearized | ✗ | ✓ |
| Tooltips that ignore Escape caught by actually hovering (1.4.13) | ✗ | ✓ |
| Legal statements for the EAA / RD 1112/2018, in Spanish and English | ✗ | ✓ |
| An evidence pack a human can countersign — hashes, matrix, empty signature block | ✗ | ✓ |
| Runs with zero dependencies at core, speaks es/en, any browser you have | heavy runtimes | ✓ |
The tools (26)
Every tool, complete — description, arguments, and behavior annotations, generated from the server itself (server.TOOLS is the source of truth). All tools accept lang (en|es) unless noted; output is JSON unless noted.
Audit
a11y_audit_url
read-only · network
Express WCAG 2.2 audit of a URL or an HTML string: 20+ automated signals with a weighted 0-100 score — images without alt (1.1.1), controls without accessible names (4.1.2), form fields without labels (3.3.2), missing autocomplete on user-data fields (1.3.5), click handlers on non-interactive elements (2.1.1), unknown ARIA roles and broken aria-labelledby (4.1.2), duplicated unnamed landmarks, timed meta refresh (2.2.1), missing skip mechanism (2.4.1), lang/title (3.1.1, 2.4.2), heading structure (1.3.1), blocked zoom (1.4.4), captions (1.2.2), autoplay audio (1.4.2), generic/duplicated link text (2.4.4), target=_blank without warning (3.2.5), positive tabindex (2.4.3), aria-hidden on focusable elements, tables without th, duplicate ids, duplicate accesskeys. Each finding includes concrete remediation. Filter, not verdict: automation covers ~1/3 of WCAG; query a11y_criterion for what a criterion means. — Prefer a11y_audit_dom when JS renders the content or contrast/2.5.8/focus matter; use pages for light multi-page sampling. Returns JSON: {mode, url|file, score 0-100, findings [{criterion, severity, signal, issue, remediation}], summary {high, medium, low}, limits, score_note}.
**Arguments**
- url: URL to fetch and audit.
- html: raw HTML to audit directly (overrides url).
- pages — range 1…20: light same-domain crawl: audit up to N pages, aggregated by score and recurring signals (default 1, max 20).
- lang — one of ['es', 'en']: output language (en default).
- timeout: fetch timeout seconds (30 default).
a11y_audit_dom
read-only · network
Deep RENDERED WCAG audit via local Playwright/Chromium: real computed text contrast against effective backgrounds with alpha compositing (1.4.3), pixel-sampled measurement of text sitting over images/gradients (background captured with the text transparent — no text pixels, no antialiasing bias), minimum target size 24×24 (2.5.8, new in WCAG 2.2), visible focus indicator heuristic (2.4.7), plus rendered versions of the static checks (alt, accessible names, labels, headings, lang/title, tabindex, aria-hidden, captions, tables). Findings include remediation. Requires playwright: pip install playwright && playwright install chromium. — Use instead of a11y_audit_url on JS-heavy pages; needs local Playwright. Returns JSON: {mode, url, score 0-100, findings [{criterion, severity, signal, issue, remediation}], summary, score_note} — same shape as the static audit.
**Arguments**
- url *(required)*: Page URL to load in Chromium (http/https or file:// for local fixtures).