Compare all ad units by key metrics to find underperformers. Use for:
AI agents call ad_unit_performance to retrieve information from AdMob MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and compares performance metrics for ad units. It is a read/query operation with no side effects. The description is truncated but clearly describes an analytical/reporting function. Severity is low as it only reads ad revenue data and cannot modify or delete anything.
From the tool's definition 'Compare all ad units by key metrics to find underperformers' — this is a read/analytical comparison of ad unit performance data
Attacks that exploit this kind of access
Compare all ad units by key metrics to find underperformers. Use for:. It is categorised as a Read tool in the AdMob MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AdMob MCP Server MCP server in PolicyLayer and add a rule for ad_unit_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 AdMob MCP Server. Nothing to install.
ad_unit_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 ad_unit_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 ad_unit_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.
ad_unit_performance is provided by the AdMob MCP Server MCP server (willhou/admob-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 →