指定したプロジェクト内のノートのコメントを削除します
AI agents call delete_project_note_comment to permanently remove resources in Repsona — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes comments from project notes without the ability to undo the action. Deletion is irreversible and represents a destructive operation. The high severity reflects that an AI agent could maliciously or accidentally delete important project discussions and collaboration history.
From the tool's definition Tool name 'delete_project_note_comment' explicitly performs deletion. Description states '指定したプロジェクト内のノートのコメントを削除します' which translates to 'deletes a comment on a note within a specified project.' The use of 'delete' (削除) indicates irreversible removal of data.
Attacks that exploit this kind of access
指定したプロジェクト内のノートのコメントを削除します. It is categorised as a Destructive tool in the Repsona MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Repsona MCP server in PolicyLayer and add a rule for delete_project_note_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 Repsona. Nothing to install.
delete_project_note_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_project_note_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_project_note_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_project_note_comment is provided by the Repsona MCP server (@bellx2/repsona-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 →