객체를 삭제합니다.
AI agents call object_delete to permanently remove resources in SVG Canvas MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes SVG objects from the design without the ability to undo through the tool itself. While the impact is scoped to a single design file (not production data or financial systems), deletion of design work represents an irreversible action that cannot be undone by the tool's own mechanisms.
From the tool's definition Tool name 'object_delete' and description '객체를 삭제합니다' (Korean: 'Deletes an object') indicate irreversible deletion of SVG objects/elements within the canvas.
Attacks that exploit this kind of access
객체를 삭제합니다. It is categorised as a Destructive tool in the SVG Canvas MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the SVG Canvas MCP server in PolicyLayer and add a rule for object_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 SVG Canvas MCP. Nothing to install.
object_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 object_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 object_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.
object_delete is provided by the SVG Canvas MCP server (kim62210/svg-canvas-mcp). 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 →