AI agents call get_site_metrics to retrieve information from Pulspeed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing performance monitoring data. It has no side effects—it does not create, modify, delete, or execute any operations. It simply returns metrics and historical analysis. This is a read-only operation with minimal blast radius even if misused by an AI agent, as it only exposes performance data already collected by the monitoring system.
From the tool's definition Tool name 'get_site_metrics' and description explicitly state it 'Get[s] performance metrics' and retrieves 'Core Web Vitals...trend analysis, and historical data over a specified period.' These are query/retrieval operations with no modification, deletion,…
Attacks that exploit this kind of access
Get performance metrics for a monitored website, including Core Web Vitals (FCP, LCP, TTI, TBT, TTFB, CLS), trend analysis, and historical data over a specified period. It is categorised as a Read tool in the Pulspeed MCP Server, which means it retrieves data without modifying state.
Register the Pulspeed MCP server in PolicyLayer and add a rule for get_site_metrics: 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 Pulspeed. Nothing to install.
get_site_metrics 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 get_site_metrics 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_metrics. 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_metrics is provided by the Pulspeed MCP server (pulspeed/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 →