// SCAN REPORT

A11y

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 03/07/2026

How to control A11y ↓

TOOL MAP

What A11y exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous A11y tools

Write · Low a11y_audit_summary The tool generates/creates a report document based on provided issues.

1 of A11y's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control A11y

PolicyLayer is an MCP gateway — it sits between your AI agents and A11y, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "a11y_audit_summary": {
    "limits": [
      {
        "counter": "a11y_audit_summary_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "a11y_check_pattern": {
    "limits": [
      {
        "counter": "a11y_check_pattern_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 A11y — 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 A11Y →

Instant setup, no code required.

FULL CATALOGUE

All 5 A11y tools

WRITE 1 tools

Write a11y_audit_summary Generate an accessibility audit report from a list of issues. Includes executive summary, severity analysis, a

READ 4 tools

Read a11y_check_pattern Analyze HTML code snippet for common accessibility issues. Returns list of issues with WCAG references and fix Read a11y_document_component Generate accessibility documentation for UI components. Includes keyboard interactions, ARIA attributes, and s Read a11y_lookup_wcag Look up WCAG criteria by number, keyword, or level. Returns criterion details including description, technique Read a11y_suggest_fix Get remediation patterns for accessibility issues. Includes before/after code examples and related patterns.

FAQ

Questions about A11y

How do I prevent bulk modifications through A11y? +

The A11y server has 1 write tools including a11y_audit_summary. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach A11y.

How many tools does the A11y MCP server expose? +

5 tools across 1 categories: Read. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on A11y? +

Register the A11y 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 A11y tool call.

Deterministic rules across all 5 A11y tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON A11Y →

Instant setup, no code required.

5 A11y tools catalogued and risk-classified — across an index of 43,000+ MCP servers.