Delete an uploaded asset from the workspace.
AI agents call plane-asset-delete to permanently remove resources in Plane — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes uploaded assets from the workspace with no undo mechanism. Deletion is irreversible and constitutes a destructive action. While the blast radius is somewhat constrained (limited to assets rather than core project data), unauthorized or erroneous deletion could cause significant data loss within a project workspace.
From the tool's definition Tool name 'plane-asset-delete' and description 'Delete an uploaded asset from the workspace' explicitly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete an uploaded asset from the workspace. It is categorised as a Destructive tool in the Plane MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Plane MCP server in PolicyLayer and add a rule for plane-asset-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 Plane. Nothing to install.
plane-asset-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 plane-asset-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 plane-asset-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.
plane-asset-delete is provided by the Plane MCP server (philipvanlewis/plane-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 →