Soft-delete multiple elements in one snapshot/commit/broadcast. All-or-nothing: if any id is missing, nothing is deleted. Duplicates are deduped. Already-deleted ids are idempotent (no error). Use this instead of calling delete_element N times.
AI agents call delete_elements 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 described as 'soft-delete' (which may imply logical deletion rather than physical removal), the tool's primary function is to delete elements from a collaborative diagram. This is irreversible in the user's workflow context—deleted diagram elements cannot be recovered through normal operations. The tool operates on multiple elements at once, amplifying the blast radius.
From the tool's definition Tool name is 'delete_elements' and description explicitly states 'Soft-delete multiple elements' and 'if any id is missing, nothing is deleted', indicating irreversible removal of data from the canvas/diagram.
Attacks that exploit this kind of access
Soft-delete multiple elements in one snapshot/commit/broadcast. All-or-nothing: if any id is missing, nothing is deleted. Duplicates are deduped. Already-deleted ids are idempotent (no error). Use this instead of calling delete_element N times. 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_elements: 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_elements 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_elements 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_elements. 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_elements 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 →