audit_site · SiteHealth MCP: Risk & Policy

WHAT IT DOES

What audit_site does on SiteHealth MCP

AI agents invoke audit_site to trigger actions in SiteHealth MCP. 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 audit_site needs a policy

The tool actively initiates outbound network operations against external targets (SSL probing, DNS lookups, email auth checks, performance testing), which constitutes executing external operations. While it is read-only in intent (auditing), it triggers real network activity whose scope and targets depend on arguments, placing it in Execute rather than Read.

From the tool's definition 'Run a comprehensive website health audit' — triggers multiple external checks (SSL, DNS, DMARC/SPF/DKIM, page performance) against a target website

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

audit_site Rate-limited

audit_site 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": {
    "audit_site": {
      "limits": [
        {
          "counter": "audit_site_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 SiteHealth MCP, so you can run agents against it safely.

FAQ

Questions about audit_site

What does the audit_site tool do? +

Run a comprehensive website health audit — SSL, DNS, DMARC/SPF/DKIM, page performance,. It is categorised as a Execute tool in the SiteHealth MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on audit_site? +

Register the SiteHealth MCP server in PolicyLayer and add a rule for audit_site: 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 SiteHealth MCP. Nothing to install.

What risk level is audit_site? +

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

Can I rate-limit audit_site? +

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

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

audit_site is provided by the SiteHealth MCP server (sitehealth-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.