Delete a comment from a document
AI agents call delete_comment to permanently remove resources in Outline — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of comments is an irreversible operation with no undo mechanism. Although the blast radius is limited to a single comment rather than entire documents, it still constitutes data destruction. Severity is medium rather than high because comments are typically lower-value metadata compared to primary document content, and the scope is narrow (one comment at a time).
From the tool's definition Tool name 'delete_comment' explicitly uses 'delete', and description states 'Delete a comment from a document' — this irreversibly removes data.
Attacks that exploit this kind of access
Delete a comment from a document. It is categorised as a Destructive tool in the Outline MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Outline MCP server in PolicyLayer and add a rule for delete_comment: 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 Outline. Nothing to install.
delete_comment 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_comment 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_comment. 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_comment is provided by the Outline MCP server (outline-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 →