AI agents call rybbit_get_performance to retrieve information from Rybbit 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 performance metrics (LCP, CLS, INP, FCP, TTFB percentiles) with optional filtering by page path, browser, or OS. The verb 'Get' and the absence of any destructive, write, execute, or financial operations confirm this is a read-only operation that has no side effects on the system or data.
From the tool's definition Tool name 'rybbit_get_performance' with description stating 'Get Core Web Vitals performance metrics' indicates data retrieval only. No modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get Core Web Vitals performance metrics (LCP, CLS, INP, FCP, TTFB) with p50, p75, p90, p99 percentiles. Optionally break down by page path, browser, or OS. It is categorised as a Read tool in the Rybbit MCP Server, which means it retrieves data without modifying state.
Register the Rybbit MCP server in PolicyLayer and add a rule for rybbit_get_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 Rybbit. Nothing to install.
rybbit_get_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 rybbit_get_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 rybbit_get_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.
rybbit_get_performance is provided by the Rybbit MCP server (nks-hub/rybbit-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 →