a11y_audit_summary · A11y MCP: Risk & Policy

WHAT IT DOES

What a11y_audit_summary does on A11y

AI agents use a11y_audit_summary to create or update resources in A11y — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A11y environment.

WHY IT NEEDS A POLICY

Why a11y_audit_summary needs a policy

The tool generates/creates a report document based on provided issues. This is a Write operation as it produces a new artifact (audit report). It doesn't execute code, delete data, or involve financial transactions. The blast radius is low since it only produces a report and does not modify any external systems or data sources.

From the tool's definition Generate an accessibility audit report from a list of issues. Includes executive summary, severity analysis, and remediation priorities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

a11y_audit_summary Rate-limited

a11y_audit_summary stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "a11y_audit_summary": {
      "limits": [
        {
          "counter": "a11y_audit_summary_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches A11y, so you can run agents against it safely.

FAQ

Questions about a11y_audit_summary

What does the a11y_audit_summary tool do? +

Generate an accessibility audit report from a list of issues. Includes executive summary, severity analysis, and remediation priorities. It is categorised as a Write tool in the A11y MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on a11y_audit_summary? +

Register the A11y MCP server in PolicyLayer and add a rule for a11y_audit_summary: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches A11y. Nothing to install.

What risk level is a11y_audit_summary? +

a11y_audit_summary is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit a11y_audit_summary? +

Yes. Add a rate_limit block to the a11y_audit_summary rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block a11y_audit_summary completely? +

Set action: deny in the PolicyLayer policy for a11y_audit_summary. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides a11y_audit_summary? +

a11y_audit_summary is provided by the A11y MCP server (shawnmcb/a11y-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.