AI agents invoke ga4.report.pivot to trigger actions in Ads. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a pivot report query against Google Analytics 4's API. While it is primarily a read/query operation, the 'Run' verb and the arbitrary body shape it accepts (per the API spec) indicate it triggers an external API operation rather than a simple retrieval. It could consume quota and process complex queries, placing it in Execute.
From the tool's definition 'Run a GA4 pivot report' — the word 'Run' indicates execution of a report query against the GA4 API, triggering an external operation
Attacks that exploit this kind of access
Run a GA4 pivot report. Body shape per developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/runPivotReport. It is categorised as a Execute tool in the Ads MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ads MCP server in PolicyLayer and add a rule for ga4.report.pivot: 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 Ads. Nothing to install.
ga4.report.pivot is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ga4.report.pivot 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 ga4.report.pivot. 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.
ga4.report.pivot is provided by the Ads MCP server (manlikemuneeb/ads-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 →