WebAbility MCP
Accessibility checks your coding agent can act on: scan a page with two engines, get a structured fix for each issue, then re-check that the fix landed.
Free. Hosted at https://mcp.webability.io/mcp. No API key for scans. MIT.
Install
Claude Code (plugin)
/plugin marketplace add snayyar00/webability-mcp
/plugin install webability-accessibility@webability
or claude mcp add --transport http webability https://mcp.webability.io/mcp
Cursor: Add to Cursor
VS Code: Install in VS Code · or run
code --add-mcp '{"name":"webability","type":"http","url":"https://mcp.webability.io/mcp"}'
Claude.ai / ChatGPT / any MCP client: add a custom connector with the URL https://mcp.webability.io/mcp.
Local (the browser runs on your machine, so it scans localhost directly): npx -y -p @webability/mcp webability-mcp
What you get back
Real output, scan_page on https://demo.vercel.store (trimmed):
Found 16 high-confidence issue(s): 0 critical, 4 serious, 8 moderate, 4 minor.
20 additional finding(s) need human review — see incomplete[]. Do NOT auto-fix these.
missing_label · serious · WCAG 1.3.1 · input.text-md.w-full.rounded-lg
fix: { op: "add-attribute", attribute: "aria-label" } fixability: contextual
missing_table_scope · moderate · WCAG 1.3.1 · thead > tr > th:nth-of-type(1) (vite.dev/guide)
fix: { op: "add-attribute", attribute: "scope", value: "col" } fixability: mechanical
verify_fix input.text-md.w-full.rounded-lg wcag=4.1.2
NOT RESOLVED: 1 violation still present → "verified": false
fix.opis one ofadd-attribute,set-attribute,remove-attribute,add-element,remove-element,add-text-content,suggest.fixability:mechanical= apply as given.contextual= the op is known, the value (alt text, a label) needs judgment.visual= needs rendered output; propose, do not auto-apply.incomplete[]holds findings that need a person (contrast over images, marketing alt text). Agents are told not to fix them.source: on React ≤18 and Vue dev builds, each issue carries{file, line, column, component}from the live component tree.verify_fixre-scans one element and fails closed.diff_scanreportsfixed[],new[],remaining[]for a page.
Free
No trial, no credits, no paid tier on the MCP.
What it does not do
It cannot judge if alt text is meaningful or if a custom widget makes sense with a screen reader. Use it to clear the automated layer in source, then test with assistive technology.
Local vs hosted
Scanning a local dev server
Use Lite (stdio). It runs the browser on your machine, so http://localhost:3000 is just localhost:
claude mcp add webability-local -- npx -y -p @webability/mcp webability-mcp
Other clients: add npx -y -p @webability/mcp webability-mcp as a stdio server.
Full (hosted) cannot reach your machine directly, by design. It runs in our cloud, so localhost there means our localhost. Every URL is checked before any fetch and loopback / private / link-local addresses are refused: without that check, anyone could point the server at internal services or a cloud metadata endpoint. That check is not relaxed for anyone.
When you need hosted: webability-tunnel
CI, a remote agent, or a dashboard-triggered scan cannot run Lite, because there is no laptop in the loop. For those, open a tunnel:
WEBABILITY_API_KEY=<your-token> npx -y -p @webability/mcp webability-tunnel --port 3000
It prints a https://tunnel.webability.io/t/<id>/ URL and a secret. Pass the URL as url and the secret as tunnel_secret:
"Scan https://tunnel.webability.io/t/abc123.../ with tunnel_secret <secret>"
Your machine dials out to the relay, so the URL is an ordinary public hostname and the SSRF check above still applies unchanged — nothing is weakened to make this work. Same idea as ngrok, with three differences that matter when the thing on the far side is your dev machine:
- The URL is not a credential. Every request must carry the secret header; the URL alone returns 401. URLs leak into shell history, CI logs and screenshots.
- Only
GETandHEADreach you, on the one port you named, andAuthorization/Cookieare stripped before anything crosses in. - It dies when you do. 30 minutes, 5 minutes idle, or the moment you press Ctrl-C.
Anyone holding both the URL and the secret can read your dev server. Treat the pair like a password, and prefer Lite whenever there is a human at a keyboard.
Third-party tunnels (ngrok, cloudflared) also work — the hosted scanner treats their hostnames like any other public site — but they expose your dev server to anyone who learns the URL. Vite users, either way: add the tunnel hostname to server.allowedHosts, or it answers 403 Blocked request to everything.
start_audit is the exception on both transports — its pipeline runs on our servers even under Lite, so it can never reach a localhost URL.
Local options
Optional env:
WEBABILITY_API_URL(defaulthttps://api.webability.io) for self-hosted backends.POSTHOG_PROJECT_API_KEYorPOSTHOG_API_KEYto enable PostHog MCP Analytics for MCP initialize, tools/list, and tool-call usage events.POSTHOG_HOST(defaulthttps://us.i.posthog.com) for EU or self-hosted PostHog ingestion.WEBABILITY_POSTHOG_MCP_ANALYTICS=offto force-disable PostHog MCP Analytics even when a PostHog key is present.
Scan engines
scan_page runs two engines in parallel and deduplicates the results:
Three-tier output (since v1.2.1)
Every scan returns:
issues— high-confidence violations, safe to surface as bugsincomplete— findings that need human review (contrast against gradients, marketing imagery, framer-motion pre-animation states, axe-incomplete). Never auto-fix these.summary— counts by severity + anincompletecount
This mirrors axe-core's violations / incomplete / passes split and prevents agents from "fixing" false positives in destructive ways.
Structured fixes (since v1.6.0)
Every issue from scan_page, flow_scan, diff_scan and scan_html carries a machine-readable fix and a fixability tier, so an agent can act without parsing prose:
{
"id": "wa-missing_button_type-a1b2c3",
"fixability": "mechanical",
"fix": { "op": "add-attribute", "attribute": "type", "value": "button", "currentValue": "", "needsManualReview": false }
}
fix.value is present only when the engine already knows it. The legacy fix.attribute / currentValue / suggestedValue / needsManualReview fields are unchanged. get_rules lists the tier for every rule so you can pick the auto-fixable set up front.
Source pointers (since v1.6.0)
On a React ≤18 or Vue dev build, scan_page, flow_scan and diff_scan read the component tree of the live page and attach the JSX call site to each finding:
{ "selector": "img#hero", "source": { "framework": "react", "file": "/app/src/Hero.tsx", "line": 12, "column": 5, "component": "Hero" } }
Open that file — no find_source round-trip. React 19 dropped _debugSource; there you still get component. Production builds have no tree; pass sourceRoot (Lite only) and issues without a pointer get sourceCandidates[] from a token grep of the selector.
Output controls (since v1.6.0)
scan_page, flow_scan, scan_html and diff_scan accept:
Filters apply before the 50-item cap, so minImpact: "serious" returns every serious issue on a 300-issue page. The scan_history archive keeps the unfiltered result.
In-process scan_html (since v1.6.0)
scan_html no longer launches a browser by default. It runs the WebAbility detectors and axe-core inside jsdom in the MCP process — milliseconds, no network — and returns the same three-tier issues / incomplete / summary shape as scan_page, with fix.op on every finding. Fragments are wrapped into a document automatically. jsdom has no layout, so visual-tier rules (contrast, target size, focus ring) are skipped and counted in skippedVisual; pass engine: "browser" for the previous headless-Chromium axe path.
Tools
When to use this MCP
- Building a new component and want it accessible from day one
- Auditing a localhost / staging build before pushing
- Triaging a Lighthouse / axe report —
scan_pageconsolidates both engines - Generating fix suggestions that match the framework you're already using
- Checking color contrast against the user's actual brand palette (not generic suggestions)
Examples
In Cursor / Claude Code:
"Scan localhost:3000 for accessibility issues"
"Walk login → dashboard → checkout and report unique issues across the flow"
"Suggest a fix for the contrast issue on
.btn-primaryon https://example.com — match their brand colors"
"What does WCAG 1.4.11 check?"
"Turn the issues you just found on localhost:3000 into a branded PDF report"
Privacy, scan logs & telemetry
Every scan is logged locally to ~/.webability/scans/ — a one-line-per-scan index.jsonl ledger plus the full result of your last 500 scans. Browse them with the scan_history tool ("what did we scan earlier?") or plain jq. Set WEBABILITY_SCAN_LOG=off to disable, WEBABILITY_SCAN_LOG_DIR to relocate.
The server also reports one small telemetry event per tool call (every tool, not just scans) to the WebAbility API: tool name, a short target label (URL, selector, issue type — never page content), pass/fail, duration, issue counts, and a persistent anonymous install ID. Full scan results, HTML, and generated fix code never leave your machine via telemetry. Set WEBABILITY_SCAN_TELEMETRY=off to opt out.
If POSTHOG_PROJECT_API_KEY or POSTHOG_API_KEY is configured, the server additionally enables PostHog MCP Analytics. This captures MCP usage metadata such as initialize, tools/list, tool name, duration, client name/version, and success/failure. WebAbility strips PostHog's $mcp_parameters and $mcp_response fields before send, so raw HTML snippets, screenshots, scan responses, and generated code are not sent to PostHog by this integration.
Two tools — generate_ai_fix and visual_audit — additionally send page content (an HTML snippet or a screenshot) to WebAbility's API so it can call a third-party LLM on your behalf; WebAbility doesn't store that content, but the LLM provider sees it in transit. See PRIVACY.md for the full per-tool breakdown and WebAbility's privacy policy.
Links
- WebAbility — platform, widget, dashboard
- Documentation
- GitHub
License
MIT
