新規ユーザーとリピーターの比較分析を行います。それぞれのセッション数や滞在時間を確認できます。
AI agents call get_new_vs_returning to retrieve information from GA4 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 analyzes existing Google Analytics 4 data to compare metrics between new and returning users. It performs read-only queries on pre-aggregated analytics data with no side effects, no state modifications, and no ability to execute code or commands. The blast radius of misuse is minimal—incorrect analysis at worst produces misleading insights about existing data.
From the tool's definition Tool description translates to 'Performs comparative analysis of new vs. returning users. You can check session counts and time spent for each.' The verbs are purely analytical/retrieval-focused ('comparison analysis,' 'confirm/check').
Attacks that exploit this kind of access
新規ユーザーとリピーターの比較分析を行います。それぞれのセッション数や滞在時間を確認できます。. It is categorised as a Read tool in the GA4 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GA4 MCP Server MCP server in PolicyLayer and add a rule for get_new_vs_returning: 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 GA4 MCP Server. Nothing to install.
get_new_vs_returning 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 get_new_vs_returning 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 get_new_vs_returning. 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.
get_new_vs_returning is provided by the GA4 MCP Server MCP server (shin-sibainu/ga4-mcp-server). 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 →