Compare search performance between two time periods. Shows which queries/pages gained or lost traffic.
AI agents call compare_performance to retrieve information from Google Search Console without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and compares historical analytics data from Google Search Console. It only reads/queries existing performance data across two time periods with no side effects, data modifications, or external operations triggered.
From the tool's definition Compare search performance between two time periods. Shows which queries/pages gained or lost traffic.
Attacks that exploit this kind of access
Compare search performance between two time periods. Shows which queries/pages gained or lost traffic. It is categorised as a Read tool in the Google Search Console MCP Server, which means it retrieves data without modifying state.
Register the Google Search Console MCP server in PolicyLayer and add a rule for compare_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 Google Search Console. Nothing to install.
compare_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 compare_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 compare_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.
compare_performance is provided by the Google Search Console MCP server (lionkiii/google-searchconsole-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 →