WCAG 2.2 Compliance

io.github.Veduis由 GitHub 账号 Veduis 发布v1.0.0更新于 Oct 30, 2026

WCAG 2.2 audits with corrected markup, verified fix examples, and U.S. ADA deadlines.

已验证STDIO仅桌面知识与记忆开发者工具

概览

AI 生成的概览

本地 MCP 服务器,可对 HTML 片段做 WCAG 2.2 审计、解释成功标准、提供已验证的修复示例,并查询美国 ADA 合规期限。

可以做什么
  • 用 18 项静态检查审计 HTML 片段或完整文档,返回未通过的准则、问题标记和修正后的代码片段
  • 查询 WCAG 2.2 成功标准的含义、符合级别、是否适用于 ADA 第二章以及是否存在自动化规则
  • 获取已验证的修复示例,包含错误片段、修正片段、原因说明和人工测试步骤
  • 按实体类型查询 ADA、Section 504、EAA 和安大略省的合规期限,并可指定某一日期计算
适用场景
适合在检查标记的无障碍缺陷、向团队解释某条 WCAG 准则,或判断某组织适用哪些无障碍期限时使用。它只是静态检查器,不能替代渲染页面测试和人工审查。
运行要求
以本地 stdio 进程运行;README 提供 npx 从 GitHub 安装、Claude Desktop 的 MCPB 包以及 Docker 构建三种方式。npx 方式需要 Node.js。无需 API 密钥、账号或网络访问,数据已内置。
安装前请注意
每次审计都返回 conformance_claim: false:结果干净只表示未发现静态缺陷,并不代表页面符合标准。对比度、焦点可见性、键盘陷阱、阅读顺序、字幕准确性和错误恢复均不在检查范围内,需要渲染页面或人工确认。README 建议完整站点审计使用其另一款商业扫描器。

安装

在 SourceWeft 中

  1. 打开 控制台中的 WCAG 2.2 Compliance,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

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.

[DOI]

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

ToolWhat it answers
audit_html_snippetWhich WCAG 2.2 defects are in this HTML, what is the failing criterion, and what does the fix look like
lookup_wcag_criterionWhat does 1.4.3 mean, what level is it, does it apply to ADA Title II entities, and is there an automated rule
get_verified_fix_exampleShow me a failing snippet, the corrected snippet, why it matters, and how to test it manually
check_ada_compliance_deadlinesWhen does my organization have to comply, and what rule sets the date

audit_html_snippet

18 static checks over a fragment or full document:

CheckSuccess criterion
Image without a text alternative1.1.1
Image button without alt1.1.1
role="img" SVG with no name1.1.1
Link with no accessible name2.4.4
Button with no accessible name4.1.2
Form field with no programmatic label3.3.2
Missing html lang3.1.1
Missing page title2.4.2
Skipped heading levels or no h11.3.1
Duplicate id values4.1.1
Positive tabindex2.4.3
aria-hidden on a focusable element4.1.2
Non-li children of ul/ol1.3.1
iframe without title4.1.2
Data table without th1.3.1
video without a captions track1.2.2
Viewport meta blocking zoom1.4.4
Common-purpose input without autocomplete1.3.5

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.

Install

bash
npx -y github:Veduis/wcag-compliance-mcp

Three other routes:

RouteCommand
MCPB bundle (Claude Desktop, one click)wcag-compliance-mcp.mcpb
Official registryio.github.Veduis/wcag-compliance-mcp
Dockerdocker build -t wcag-compliance-mcp . && docker run -i --rm wcag-compliance-mcp

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):

json
{  "mcpServers": {    "wcag-compliance": {      "command": "npx",      "args": ["-y", "github:Veduis/wcag-compliance-mcp"]    }  }}

Cursor

.cursor/mcp.json:

json
{  "mcpServers": {    "wcag-compliance": {      "command": "npx",      "args": ["-y", "github:Veduis/wcag-compliance-mcp"]    }  }}

VS Code (Copilot agent mode)

.vscode/mcp.json:

json
{  "servers": {    "wcag-compliance": {      "command": "npx",      "args": ["-y", "github:Veduis/wcag-compliance-mcp"]    }  }}

Docker

bash
docker build -t wcag-compliance-mcp .docker run -i --rm wcag-compliance-mcp

Example

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

DatasetDOI
Preprint: what automated testing actually detects10.5281/zenodo.23829968
64 browser-verified fail/pass pairs, axe-core 4.14.010.5281/zenodo.23781867
87 WCAG 2.2 success criteria with rule mapping10.5281/zenodo.23781861
21 sourced ADA / Section 504 / EAA dates10.5281/zenodo.23781873
64 multi-turn LLM remediation prompts10.5281/zenodo.23781879

Mirrors: Hugging Face. Test cases are CC BY 4.0, code is MIT.

Development

bash
npm installnpm test          # 18 checks, including a live stdio handshakenpm start

Layout:

src/index.mjs    MCP server, tool registration, resourcesrc/checks.mjs   18 static checks, no browser requiredsrc/data.mjs     criteria, pairs, timeline, deadline resolutiondata/            bundled JSON, generated from the published datasetstest/smoke.mjs   engine tests plus protocol handshake

More from Veduis

License

MIT for the code. Dataset content is CC BY 4.0, attribution to Veduis LLC.

来源:README.md,提交 3612c03

工具

0
SourceWeft 曾在隔离沙箱中以无凭据方式启动该软件包一次,以列出其工具,但未能完成:该软件包类型无法在沙箱中运行。

版本历史

1
  1. v1.0.0最新Oct 30, 2026

评分

已满足适用检查项的 40%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。