Measure TTFB, total load time, page weight, redirect chain, compression, and cache headers.
AI agents call check_performance to retrieve information from SiteHealth MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes website performance data without creating, modifying, deleting, or executing operations. It is purely diagnostic and informational, analogous to a performance profiling query. No state changes occur on the target system. Even if misused, an AI agent cannot cause harm by repeatedly calling this read-only diagnostic tool.
From the tool's definition Tool measures and reports on performance metrics (TTFB, load time, page weight, redirect chain, compression, cache headers) with no side effects described.
Attacks that exploit this kind of access
Measure TTFB, total load time, page weight, redirect chain, compression, and cache headers. It is categorised as a Read tool in the SiteHealth MCP MCP Server, which means it retrieves data without modifying state.
Register the SiteHealth MCP server in PolicyLayer and add a rule for check_performance: 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.
check_performance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_performance 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 check_performance. 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.
check_performance 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.
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 →