Delete an ad. DESTRUCTIVE.
AI agents call delete_ad 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 permanently removes an ad from Meta's advertising system. Deletion is irreversible and cannot be undone. While not directly financial, deleting an ad can cause business harm (loss of active campaigns, disruption to marketing efforts). The high severity reflects the potential for an AI agent to inadvertently or maliciously delete active, revenue-generating ads.
From the tool's definition Tool name 'delete_ad' combined with description explicitly stating 'DESTRUCTIVE' indicates irreversible deletion of advertising content.
Attacks that exploit this kind of access
Delete an ad. 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_ad: 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_ad 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_ad 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_ad. 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_ad 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 →