Clicks, cost, CTR, conversions, and CPA split by MOBILE / DESKTOP / TABLET per campaign. Default last 28 days.
AI agents call gads_device_performance to retrieve information from Google Ads without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves performance metrics (clicks, cost, CTR, conversions, CPA) segmented by device type. This is purely a read/reporting operation with no side effects, data modification, or financial transactions.
From the tool's definition Clicks, cost, CTR, conversions, and CPA split by MOBILE / DESKTOP / TABLET per campaign. Default last 28 days.
Attacks that exploit this kind of access
Clicks, cost, CTR, conversions, and CPA split by MOBILE / DESKTOP / TABLET per campaign. Default last 28 days. It is categorised as a Read tool in the Google Ads MCP Server, which means it retrieves data without modifying state.
Register the Google Ads MCP server in PolicyLayer and add a rule for gads_device_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 Ads. Nothing to install.
gads_device_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 gads_device_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 gads_device_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.
gads_device_performance is provided by the Google Ads MCP server (zleventer/google-ads-mcp-npm). 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 →