Soft-delete all non-deleted elements belonging to a groupId in one snapshot/commit/broadcast. Returns { deletedElementIds }. Returns empty array if the group has no live members.
AI agents call delete_group to permanently remove resources in Whiteboard — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although characterized as 'soft-delete' rather than hard deletion, the tool irreversibly removes elements from active use in the diagram. Soft-deletes are still destructive operations that cannot be automatically reversed by the user. The blast radius is high if an agent misuses this on a shared collaborative canvas, as all elements in a group are deleted in a single operation.
From the tool's definition Tool name contains 'delete' and description explicitly states 'Soft-delete all non-deleted elements belonging to a groupId' — this removes data from the canvas, even if soft-deleted rather than permanently purged.
Attacks that exploit this kind of access
Soft-delete all non-deleted elements belonging to a groupId in one snapshot/commit/broadcast. Returns { deletedElementIds }. Returns empty array if the group has no live members. It is categorised as a Destructive tool in the Whiteboard MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Whiteboard MCP server in PolicyLayer and add a rule for delete_group: 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 Whiteboard. Nothing to install.
delete_group 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_group 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_group. 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_group is provided by the Whiteboard MCP server (kamiazya/whiteboard). 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 →