Combined GSC + GA4 performance analysis for a date range
AI agents call combined_performance_report to retrieve information from MCP Search Analytics Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves combined analytics data from two read-only data sources (GSC and GA4). It performs analysis over a date range, which is a read/reporting operation with no side effects, writes, or destructive actions. Misuse risk is low as it only exposes analytics metrics.
From the tool's definition 'performance analysis' and 'GSC + GA4' indicate retrieval of analytics data from Google Search Console and Google Analytics 4 for a date range
Attacks that exploit this kind of access
Combined GSC + GA4 performance analysis for a date range. It is categorised as a Read tool in the MCP Search Analytics Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Search Analytics Server MCP server in PolicyLayer and add a rule for combined_performance_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 MCP Search Analytics Server. Nothing to install.
combined_performance_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 combined_performance_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 combined_performance_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.
combined_performance_report is provided by the MCP Search Analytics Server MCP server (vesivanov/mcp-search-analytics). 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 →