Build aggregated analytics report with custom dimensions, measures,
AI agents call keitaro_build_report to retrieve information from Keitaro MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates analytics data (dimensions, measures) for reporting purposes. It queries existing data without creating, modifying, or deleting anything. Severity is medium because the report could expose sensitive traffic and conversion data, but there are no destructive or write side effects.
From the tool's definition Build aggregated analytics report with custom dimensions, measures
Attacks that exploit this kind of access
Build aggregated analytics report with custom dimensions, measures,. It is categorised as a Read tool in the Keitaro MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Keitaro MCP Server MCP server in PolicyLayer and add a rule for keitaro_build_report: 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 Keitaro MCP Server. Nothing to install.
keitaro_build_report 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 keitaro_build_report 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 keitaro_build_report. 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.
keitaro_build_report is provided by the Keitaro MCP Server MCP server (keitaromanager/keitaro-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 →