Search response time percentiles (p50/p95/p99), cache hit rate, autocomplete usage rate,
AI agents call search_performance to retrieve information from Mcp Revelor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns analytics data about search performance without modifying any data or triggering external operations. It is purely observational/monitoring in nature, fitting the Read category. The low severity reflects minimal impact even if misused—returning metrics poses no direct risk to data integrity, financial systems, or operations.
From the tool's definition Tool name 'search_performance' and description indicate it retrieves metrics: 'Search response time percentiles (p50/p95/p99), cache hit rate, autocomplete usage rate'. No modification, deletion, or execution capability is described.
Attacks that exploit this kind of access
Search response time percentiles (p50/p95/p99), cache hit rate, autocomplete usage rate,. It is categorised as a Read tool in the Mcp Revelor MCP Server, which means it retrieves data without modifying state.
Register the Mcp Revelor MCP server in PolicyLayer and add a rule for search_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 Mcp Revelor. Nothing to install.
search_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 search_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 search_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.
search_performance is provided by the Mcp Revelor MCP server (webotvurci-s-r-o/mcp-revelor). 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 →