I turned my accessibility checker into an MCP server, so the agent that writes the HTML can also fix it

A developer released a11yscope-mcp, an MCP server that wraps their WCAG accessibility checker so coding agents like Claude Code and Cursor can scan and fix generated HTML. The server exposes three tools — scan_page, scan_html and list_rules — covering 31 checks mapped to WCAG 2.2 success criteria, runs entirely locally using an existing Chrome, Chromium, Edge or Brave install, and returns undecidable items as "review" rather than pass. The engine returns zero violations on gov.uk, webaim.org, deque.com, a11yproject.com and w3.org/WAI, which the developer treats as an acceptance test.

Last week I wrote about running my WCAG checker against gov.uk https://dev.to/perceivable/i-ran-my-accessibility-checker-against-govuk-it-found-72-violations-all-of-them-were-mine-5fp0 and finding that every one of the 72 "violations" was a bug in my checker. Fixing those left me with an engine I trust on real sites, packaged as a Chrome extension. But the people who most need an accessibility check right now are not people. They are coding agents. Claude Code, Cursor and friends generate a huge share of new HTML, and they ship <img without alt , grey-on-white placeholders and outline: none just like we did, only faster. An extension that a human clicks does nothing for that. So the same engine is now an MCP server: a11yscope-mcp . Three tools: scan page loads a URL or a local HTML file in headless Chrome and returns violations grouped by rule. Every finding has a CSS selector, an HTML snippet and a message that says what to change. scan html does the same for a string of markup, which is the one agents actually need: list rules returns the 31 checks with the WCAG 2.2 success criteria they map to. The checks cover text alternatives images, labels, buttons, links, frames, SVG , colour contrast with the large-text and bold exemptions applied and translucent backgrounds composited, document structure language, title, heading order, main landmark, skip link, tables, lists , and keyboard, pointer and ARIA zoom lock, positive tabindex, aria-hidden focusables, nested controls, the new 24×24 target size, autoplay, captions, invalid roles, required ARIA states, autocomplete, removed focus outlines . Everything runs locally. It uses the Chrome, Chromium, Edge or Brave you already have, downloads nothing at install time, sends nothing anywhere. Claude Code: claude mcp add a11yscope -- npx -y a11yscope-mcp Cursor, Claude Desktop or any other MCP client: { "mcpServers": { "a11yscope": { "command": "npx", "args": "-y", "a11yscope-mcp" } } } Then a prompt like "scan http://localhost:3000 http://localhost:3000 with a11yscope and fix every violation, then scan again" closes the loop: the agent reads the selector and the message, edits the file, and re-scans until the list is empty. For a component with an unlabelled image and an empty link: { "summary": { "violations": 2, "review": 1, "rulesRun": 31, "rulesFailed": 2, "rulesPassed": 28 }, "rules": { "id": "img-alt", "wcag": "1.1.1" , "level": "A", "impact": "critical", "help": "Add alt text describing what the image conveys. If the image is purely decorative, use alt=\"\" ...", "violations": { "selector": "html body main img", "message": "<img has no alt attribute src: a.png ", "snippet": "<img src=\"a.png\" width=\"120\" height=\"80\" " } }, { "id": "link-name", "wcag": "2.4.4", "4.1.2" , "level": "A", "impact": "critical", "violations": { "selector": "html body main a", "message": "Link has no discernible text", "snippet": "<a href=\"/x\" " } } , "disclaimer": "Automated checks find roughly a third of accessibility barriers. A clean result is a good sign, not a conformance claim; items marked review need a human decision." } That disclaimer is in every response on purpose. An agent will happily tell its user "the page is now WCAG compliant" if you let it. Roughly a third of barriers are machine-checkable; whether the alt text is true , whether the page makes sense in a screen reader, whether a keyboard user can finish the checkout, no tool can say. Anything the engine cannot decide comes back as review , not as pass. The gov.uk exercise became the acceptance test. gov.uk, webaim.org, deque.com, a11yproject.com and w3.org/WAI all return zero violations from this engine. Anything reported on those sites is treated as my bug until proven otherwise. If you hit a false positive, the issue tracker is the most useful place to put it: https://github.com/perceivable/a11yscope/issues https://github.com/perceivable/a11yscope/issues