Audit the entire ad account for wasted spend. Scans all entities (keywords, audiences, creatives, ad groups) across all campaigns over the last N days. Flags any entity whose spend exceeds a threshold while generating zero (or near-zero) conversions, or whose CPA is far above the account average....
AI agents call audit_account_waste to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs retrospective analysis and reporting on advertising metrics. While it may inform business decisions about budget allocation, it does not itself modify accounts, delete entities, execute campaigns, or commit financial transactions. The scanning and flagging are informational operations.
From the tool's definition Tool scans and analyzes ad account data to identify wasted spend patterns, returning a 'prioritized list ordered by wasted spend' with no modification of underlying data.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Audit the entire ad account for wasted spend. Scans all entities (keywords, audiences, creatives, ad groups) across all campaigns over the last N days. Flags any entity whose spend exceeds a threshold while generating zero (or near-zero) conversions, or whose CPA is far above the account average. Returns a prioritized list ordered by wasted spend (highest first), plus the total amount wasted and what % of total account spend that represents. Args: - days (number, optional): Lookback window in days. Default 30. - min_spend_cents (number, optional): Minimum total spend (in cents) for an entity to be considered. Default 5000 (€50). - max_conversions (number, optional): Entities with conversions <= this are flagged. Default 0. - cpa_multiplier (number, optional): Also flag entities whose CPA is greater than this multiple of the account average CPA. Default 3. Examples: -. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for audit_account_waste: 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 Postgres. Nothing to install.
audit_account_waste 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 audit_account_waste 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 audit_account_waste. 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.
audit_account_waste is provided by the Postgres MCP server (santisanti13/postgres-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 →