Remove a comment (DELETE /articles/{article_id}/comments/{comment_id}).
AI agents call comment_delete to permanently remove resources in Voog — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes a comment via a DELETE HTTP request. This is an irreversible action with no indication of soft-delete or recovery mechanism, placing it firmly in the Destructive category. Severity is medium since the blast radius is limited to individual comments rather than entire pages or datasets.
From the tool's definition 'Remove a comment' and 'DELETE /articles/{article_id}/comments/{comment_id}' — explicitly uses HTTP DELETE to irreversibly remove a comment resource.
Attacks that exploit this kind of access
Remove a comment (DELETE /articles/{article_id}/comments/{comment_id}). It is categorised as a Destructive tool in the Voog MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Voog MCP server in PolicyLayer and add a rule for comment_delete: 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 Voog. Nothing to install.
comment_delete 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 comment_delete 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 comment_delete. 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.
comment_delete is provided by the Voog MCP server (runnel/voog-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 →