Run a technical SEO audit on a URL. Returns page performance, meta tags, headings, images, links, and more. Uses audit credits.
AI agents invoke get_site_audit to trigger actions in Zutrix MCP Server. 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.
The tool actively runs an audit process against a URL, consuming credits and triggering external operations. This goes beyond a simple read/query of existing data — it executes a crawl/audit job. The credit consumption also implies a resource commitment.
From the tool's definition 'Run a technical SEO audit on a URL' and 'Uses audit credits' indicate this triggers an active external operation (crawling/auditing a URL) rather than merely retrieving stored data.
Attacks that exploit this kind of access
Run a technical SEO audit on a URL. Returns page performance, meta tags, headings, images, links, and more. Uses audit credits. It is categorised as a Execute tool in the Zutrix MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Zutrix MCP Server MCP server in PolicyLayer and add a rule for get_site_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 Zutrix MCP Server. Nothing to install.
get_site_audit is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the get_site_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.
Set action: deny in the PolicyLayer policy for get_site_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.
get_site_audit is provided by the Zutrix MCP Server MCP server (zutrix-technologies/zutrix-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →