Delete an ad set. DESTRUCTIVE.
AI agents call delete_adset to permanently remove resources in Claude Meta — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes ad set data in Meta Ads systems. Once deleted, the ad set and its associated settings are gone and must be manually recreated. This is a destructive action with significant blast radius—an AI agent misdirected could eliminate active marketing campaigns. The explicit 'DESTRUCTIVE' label in the description confirms this classification.
From the tool's definition Tool name is 'delete_adset' and description explicitly states 'Delete an ad set. DESTRUCTIVE.' The tool removes ad set configurations that cannot be recovered without manual recreation.
Attacks that exploit this kind of access
Delete an ad set. DESTRUCTIVE. It is categorised as a Destructive tool in the Claude Meta MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Meta MCP server in PolicyLayer and add a rule for delete_adset: 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 Claude Meta. Nothing to install.
delete_adset is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_adset 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 delete_adset. 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.
delete_adset is provided by the Claude Meta MCP server (maxx3250/claude-meta-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 →