Delete (or rather: soft-delete) a campaign by setting its status to DELETED. DESTRUCTIVE.
AI agents call delete_campaign 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.
Although characterized as a 'soft-delete' (status change rather than permanent data erasure), this tool irreversibly removes a campaign from active use. Campaign deletion cannot be easily undone and represents a significant business impact—it stops ad delivery, halts budget spending, and removes marketing assets from operation.
From the tool's definition Tool description explicitly states "Delete (or rather: soft-delete) a campaign by setting its status to DELETED. DESTRUCTIVE." The description directly uses the term DESTRUCTIVE and describes removal of a campaign resource.
Attacks that exploit this kind of access
Delete (or rather: soft-delete) a campaign by setting its status to DELETED. 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_campaign: 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_campaign 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_campaign 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_campaign. 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_campaign 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 →