Delete an Excalidraw element
AI agents call delete_element to permanently remove resources in Excalidraw MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete_element tool performs irreversible deletion of diagram elements. While the blast radius is contained to the Excalidraw canvas (not system-wide or financial), an AI agent could maliciously or erroneously delete critical diagram content that cannot be recovered through the tool API alone.
From the tool's definition Tool name explicitly 'delete_element' with description 'Delete an Excalidraw element'. The delete operation irreversibly removes elements from the canvas.
Attacks that exploit this kind of access
Delete an Excalidraw element. It is categorised as a Destructive tool in the Excalidraw MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Excalidraw MCP Server MCP server in PolicyLayer and add a rule for delete_element: 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 Excalidraw MCP Server. Nothing to install.
delete_element 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_element 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_element. 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_element is provided by the Excalidraw MCP Server MCP server (kakacoding1/mcp_excalidraw). 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 →