Delete an attachment from a page.
AI agents call delete_attachment to permanently remove resources in Collectives — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes an attachment, which cannot be undone. Destructive category applies because the action irreversibly deletes data. Severity is high because unintended deletion of attachments could impact collaborative documentation, though the blast radius is narrower than deleting entire pages or collectives. Confidence is high due to the explicit delete operation in both name and description.
From the tool's definition delete_attachment: Delete an attachment from a page. The name and description explicitly indicate irreversible deletion of data (an attachment).
Attacks that exploit this kind of access
Delete an attachment from a page. It is categorised as a Destructive tool in the Collectives MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Collectives MCP server in PolicyLayer and add a rule for delete_attachment: 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 Collectives. Nothing to install.
delete_attachment 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_attachment 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_attachment. 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_attachment is provided by the Collectives MCP server (megamaced/nc_collectives-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 →