// SCAN REPORT

A11ychk

6 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 30 Sept 2026

0 can modify or destroy data

6 read-only

6 tools total

Community server · catalogue entry checked 30/09/2026

How to control A11ychk ↓

TOOL MAP

What A11ychk exposes to your agents

Read (6) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control A11ychk

PolicyLayer is an MCP gateway — it sits between your AI agents and A11ychk, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "crawl_sample": {
    "limits": [
      {
        "counter": "crawl_sample_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register A11ychk — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON A11YCHK →

Instant setup, no code required.

FULL CATALOGUE

All 6 A11ychk tools

READ 6 tools

Read crawl_sample 사이트의 sitemap·내부 링크에서 대표 페이지 표본을 뽑는다 (WCAG-EM 방식 층화 표집, robots.txt 존중). Read get_fix_guide 검사 규칙(axe/자체 규칙) 하나의 한국어 개선 가이드와 WCAG·KWCAG 매핑을 조회한다. Read kwcag_checkpoint KWCAG 2.2 검사항목(33개) 하나의 검사 방법·대응 WCAG 성공기준·자동 판정 규칙을 조회한다. Read scan_dir 로컬 디렉터리의 정적 HTML 파일들을 재귀 수집해 일괄 검사한다 (최대 ${SCAN_MAX_URLS}개, Read scan_page 웹 페이지 1개를 WCAG 2.2 AA + KWCAG 2.2 기준으로 검사한다 (axe-core + 자체 규칙). Read scan_pages 웹 페이지 여러 개(최대 ${SCAN_MAX_URLS}개)를 한 번에 검사한다. crawl_sample이 수집한 표본을 넣기 좋다.

FAQ

Questions about A11ychk

Is the A11ychk MCP server safe to use without restrictions? +

The A11ychk server is primarily read-only with 6 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the A11ychk MCP server expose? +

6 tools across 1 categories: Read. 6 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on A11ychk? +

Register the A11ychk MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every A11ychk tool call.

Deterministic rules across all 6 A11ychk tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON A11YCHK →

Instant setup, no code required.

6 A11ychk tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from A11ychk's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →