Soft-delete all non-deleted elements on the canvas in one snapshot/commit/broadcast. Tombstone semantics identical to delete_element. Returns { clearedCount }. Idempotent: a second call on an empty canvas returns 0.
AI agents call canvas_clear 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.
This tool clears an entire canvas of all elements in a single operation. While 'soft-delete' and tombstone semantics suggest recoverable deletion, the tool irreversibly removes user work in bulk without granular control. The high severity reflects potential loss of collaborative diagrams and work products, making this Destructive rather than merely Write. An agent misusing this could wipe shared whiteboard content.
From the tool's definition 'Soft-delete all non-deleted elements on the canvas in one snapshot/commit/broadcast' — irreversibly removes all diagram content; 'Tombstone semantics identical to delete_element' confirms deletion semantics; 'Idempotent' indicates state change is permanent.
Attacks that exploit this kind of access
Soft-delete all non-deleted elements on the canvas in one snapshot/commit/broadcast. Tombstone semantics identical to delete_element. Returns { clearedCount }. Idempotent: a second call on an empty canvas returns 0. 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 canvas_clear: 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.
canvas_clear 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 canvas_clear 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 canvas_clear. 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.
canvas_clear 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 →