wcag-compliance-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@wcag-compliance-mcp Audit this HTML for WCAG 2.2 issues: <img src="chart.png">"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
wcag-compliance-mcp
MCP server for WCAG 2.2 audits, verified remediation examples, and U.S. accessibility deadlines. Four tools, no API keys, no network calls, all data bundled.
Built from a benchmark that was verified in headless Chromium: 64 fail/pass HTML pairs executed against axe-core 4.14.0, all 87 WCAG 2.2 success criteria, and 21 sourced regulatory dates from the 1990 ADA through the 2028 DOJ Title II deadline.
Listed in the official MCP registry as io.github.Veduis/wcag-compliance-mcp, on the 97k star MCP directory, and in the accessibility tools list.
Tools
Tool | What it answers |
| Which WCAG 2.2 defects are in this HTML, what is the failing criterion, and what does the fix look like |
| What does 1.4.3 mean, what level is it, does it apply to ADA Title II entities, and is there an automated rule |
| Show me a failing snippet, the corrected snippet, why it matters, and how to test it manually |
| When does my organization have to comply, and what rule sets the date |
audit_html_snippet
18 static checks over a fragment or full document:
Check | Success criterion |
Image without a text alternative | 1.1.1 |
Image button without alt | 1.1.1 |
| 1.1.1 |
Link with no accessible name | 2.4.4 |
Button with no accessible name | 4.1.2 |
Form field with no programmatic label | 3.3.2 |
Missing | 3.1.1 |
Missing page title | 2.4.2 |
Skipped heading levels or no h1 | 1.3.1 |
Duplicate | 4.1.1 |
Positive | 2.4.3 |
| 4.1.2 |
Non- | 1.3.1 |
| 4.1.2 |
Data table without | 1.3.1 |
| 1.2.2 |
Viewport meta blocking zoom | 1.4.4 |
Common-purpose input without | 1.3.5 |
Every finding returns the criterion, the offending markup, and a corrected snippet.
check_ada_compliance_deadlines
Entity types: title_ii_large, title_ii_small, title_iii_business, federal_contractor, hhs_recipient, eu_business, ontario.
Pass as_of to compute the answer for any date, which makes the tool useful for retroactive scoping and for legal memos that need to state what applied on a given day. Every date carries its primary source URL.
Related MCP server: accessibility-mcp-server
Install
npx -y github:Veduis/wcag-compliance-mcpThree other routes:
Route | Command |
MCPB bundle (Claude Desktop, one click) | |
Official registry |
|
Docker |
|
The npm package wcag-compliance-mcp lands with the next publish. Until then the GitHub spec installs the same code and dependencies.
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"wcag-compliance": {
"command": "npx",
"args": ["-y", "github:Veduis/wcag-compliance-mcp"]
}
}
}Cursor
.cursor/mcp.json:
{
"mcpServers": {
"wcag-compliance": {
"command": "npx",
"args": ["-y", "github:Veduis/wcag-compliance-mcp"]
}
}
}VS Code (Copilot agent mode)
.vscode/mcp.json:
{
"servers": {
"wcag-compliance": {
"command": "npx",
"args": ["-y", "github:Veduis/wcag-compliance-mcp"]
}
}
}Docker
docker build -t wcag-compliance-mcp .
docker run -i --rm wcag-compliance-mcpExample
Ask your agent:
Audit this pricing page for WCAG 2.2 issues and give me the corrected markup.
The agent calls audit_html_snippet, then get_verified_fix_example for each failing criterion. What comes back is a failing snippet, the corrected snippet, and the manual test step, not a vague warning.
$ audit_html_snippet('<img src="chart.png">')
{
"summary": {
"issues": 1,
"checks_run": 18,
"checks_failed": 1,
"conformance_claim": false
},
"findings": [
{
"check_id": "img-alt",
"sc": "1.1.1",
"level": "A",
"title": "Image missing a text alternative",
"count": 1,
"elements": [
{
"snippet": "<img src=\"chart.png\">",
"reason": "No alt, aria-label, or aria-labelledby. Decorative images need alt=\"\"."
}
],
"fix": "<img src=\"chart.png\" alt=\"Bar chart: Q3 revenue rose 18 percent over Q2\">"
}
]
}What automation cannot see
This matters more than the feature list. In the benchmark behind this server, axe-core 4.14.0 flagged 39 of 64 deliberately defective documents. The other 25 needed scripted checks or a human. Across the full standard, 29 of 87 criteria have a mapped rule and 58 have none, and at Level AA, the level the law actually targets, only 7 of 24 criteria have a rule.
So the server reports conformance_claim: false on every audit. A clean result means no static defect was found, not that the page conforms. Contrast, focus visibility, keyboard traps, reading order, captions accuracy, and error recovery all need a rendered page or a person. If you need a full-domain audit with those checks, that is what vComplianceScanner does.
Data provenance
Dataset | DOI |
Preprint: what automated testing actually detects | |
64 browser-verified fail/pass pairs, axe-core 4.14.0 | |
87 WCAG 2.2 success criteria with rule mapping | |
21 sourced ADA / Section 504 / EAA dates | |
64 multi-turn LLM remediation prompts |
Mirrors: Hugging Face. Test cases are CC BY 4.0, code is MIT.
Development
npm install
npm test # 18 checks, including a live stdio handshake
npm startLayout:
src/index.mjs MCP server, tool registration, resource
src/checks.mjs 18 static checks, no browser required
src/data.mjs criteria, pairs, timeline, deadline resolution
data/ bundled JSON, generated from the published datasets
test/smoke.mjs engine tests plus protocol handshakeMore from Veduis
License
MIT for the code. Dataset content is CC BY 4.0, attribution to Veduis LLC.
Available Tools
4 toolsaudit_html_snippetAudit HTML for WCAG 2.2 defectsA
Run 18 static WCAG 2.2 checks against an HTML snippet or full page and return findings with the failing success criterion, the offending markup, and a corrected example. Covers alt text, accessible names for links and buttons, form labels, language, title, heading order, duplicate ids, tabindex, aria-hidden, list structure, iframe titles, table headers, video captions, viewport zoom, and autocomplete purpose. Static analysis only: it cannot judge contrast, keyboard traps, focus visibility, or reading order in a rendered page.
Inputs: html (required), severity_floor.
check_ada_compliance_deadlinesCheck ADA / Section 504 web accessibility deadlinesA
Return the dated web accessibility obligations that apply to an entity type, from the 1990 ADA statute through the 2027 and 2028 deadlines in the DOJ Title II final rule and the HHS Section 504 rule. Reports what is binding now, what is upcoming within the horizon with days remaining, and the primary source URL for every date. Entity types: title_ii_large, title_ii_small, title_iii_business, federal_contractor, hhs_recipient, eu_business, ontario.
Inputs: entity_type (required), as_of, horizon_years.
get_verified_fix_exampleGet a browser-verified WCAG fix exampleA
Return a failing HTML snippet and its corrected version for a WCAG 2.2 defect, with an explanation of the impact on assistive technology and a manual test step. Every pair was executed in headless Chromium against axe-core 4.14.0, and the detection method is reported so you know whether automation catches this defect or a human must. Look up by criterion number (2.4.7), pair id (wcag-1-4-3-01), or keyword (focus indicator).
Inputs: limit, query, sc_id.
lookup_wcag_criterionLook up a WCAG 2.2 success criterionA
Search the 87 WCAG 2.2 success criteria by number (1.4.3), name (Contrast), keyword, or axe-core rule name. Returns level, principle, guideline, whether it applies to U.S. ADA Title II entities, the practical test, the axe-core rules that target it, and links to the W3C specification and Understanding document.
Inputs: query (required), level, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a clearly distinct operation: static auditing, criterion lookup, verified fix examples, and ADA deadline checking. Although audit_html_snippet and get_verified_fix_example both involve defects and corrections, their descriptions distinguish audit results from a curated remediation library.
All four tools use a consistent snake_case verb_noun pattern: audit_html_snippet, lookup_wcag_criterion, get_verified_fix_example, and check_ada_compliance_deadlines. The naming is predictable and readable.
Four tools is a well-scoped set for this domain, with each tool covering a substantial but distinct compliance function. There is no filler or redundant tool.
The surface covers static auditing, WCAG reference lookup, remediation examples, and legal deadlines, which are the core needs for WCAG/ADA compliance support. The main gap is the acknowledged lack of rendered-page checks such as contrast, keyboard traps, and focus visibility, but that limitation is explicit rather than hidden.
Maintenance
Related MCP Connectors
Scan URLs or HTML for WCAG 2.2 violations. 75-rule manifest, weighted score, shareable reports.
Accessibility compliance for AI coding tools. WCAG 2.2 reviews with shared evidence.
Scan URLs for WCAG 2.1 violations, generate AI fixes, and produce VPAT 2.5 compliance reports.
Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides conversational, actionable accessibility testing for AI agents, including auditing, prioritization, and code-level fixes.22MIT
- AlicenseAqualityDmaintenanceEnables AI agents to perform comprehensive web accessibility checks (WCAG 2.1/2.2) including color contrast analysis, ARIA validation, and full accessibility report generation without requiring any API key.824 PyPIMIT
- AlicenseAqualityBmaintenanceEnables AI agents to perform WCAG 2.2 accessibility audits, including contrast ratio checks for color pairs and text-over-image, generate EU legal accessibility declarations, and produce aria-live monitoring snippets, all through local, multilingual tools.37477 PyPI7MIT
- AlicenseAqualityBmaintenanceLets developers and MCP agents run deterministic local HTML audits, turning inline HTML into structured findings for missing labels, unnamed buttons, skipped headings, ambiguous links, duplicate IDs, and missing landmarks. It also exposes a rule list and returns stable, actionable reports without external API keys.2MIT