Autonomous WCAG 2.1 accessibility auditor that scans, fixes, re-verifies, and generates VPAT 2.5 EN 301 549 reports using AI vision analysis + DOM scanning.
Accessibilityai is an MCP project maintained in the groundlogic-ai-source/accessibility-ai repository. The maintainer describes its purpose as “Autonomous WCAG 2.1 accessibility auditor that scans, fixes, re-verifies, and generates VPAT 2.5 EN 301 549 reports using AI vision analysis + DOM scanning”. Read the project documentation for the complete scope.
The maintainer’s configuration uses https://your-deployed-instance.com/mcp. Check the project’s account and authentication instructions when adding the endpoint to your client.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| scan_accessibility | |
| generate_fixes | |
| re_verify | |
| generate_vpat |
{
"mcpServers": {
"accessibility-ai": {
"url": "https://your-deployed-instance.com/mcp",
"transport": "streamable-http"
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Identifies accessibility issues in web applications using AI agents and comprehensive testing.
Manages notes with a robust Model Context Protocol (MCP) server.
Alt text, headings, contrast, ARIA for AI agents
Real-browser WCAG audit that also finds keyboard-inoperable controls axe-core misses, with fixes.