Recommendation engine performance: impressions, CTR, conversion rate, top clicked recommended products.
AI agents call recommendation_metrics 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.
The tool queries and retrieves performance data from the recommendation engine. The description indicates it reports metrics and statistics (impressions, click-through rates, conversion rates, popular products) without creating, modifying, deleting, or executing operations. This is a straightforward data retrieval operation typical of analytics endpoints.
From the tool's definition Tool retrieves recommendation engine performance metrics: 'impressions, CTR, conversion rate, top clicked recommended products'. These are analytics queries with no modification or side effects.
Attacks that exploit this kind of access
Recommendation engine performance: impressions, CTR, conversion rate, top clicked recommended products. 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 recommendation_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 Mcp Revelor. Nothing to install.
recommendation_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 recommendation_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 recommendation_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.
recommendation_metrics 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 →