run_page_audit · Web Audit MCP: Risk & Policy

WHAT IT DOES

What run_page_audit does on Web Audit

AI agents invoke run_page_audit to trigger actions in Web Audit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_page_audit needs a policy

This tool executes audit operations (scanning, analysis, metrics collection) against web pages. While described as 'safe' and 'non-invasive', it still represents an Execute action because it triggers external operations whose effects depend on the target URL argument.

From the tool's definition Tool description states 'Run a safe non-invasive page audit' — the verb 'Run' indicates code execution or automated operations against a target URL.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_page_audit Rate-limited

run_page_audit stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_page_audit": {
      "limits": [
        {
          "counter": "run_page_audit_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about run_page_audit

What does the run_page_audit tool do? +

Run a safe non-invasive page audit and return scores, metrics, and prioritized findings. It is categorised as a Execute tool in the Web Audit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_page_audit? +

Register the Web Audit MCP server in PolicyLayer and add a rule for run_page_audit: 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 Web Audit. Nothing to install.

What risk level is run_page_audit? +

run_page_audit is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_page_audit? +

Yes. Add a rate_limit block to the run_page_audit 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 run_page_audit completely? +

Set action: deny in the PolicyLayer policy for run_page_audit. 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 run_page_audit? +

run_page_audit is provided by the Web Audit MCP server (sayuru-akash/web-audit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.