AI agents call delete_shape to permanently remove resources in Tl Draw — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion is irreversible; once a shape is deleted, it cannot be recovered through normal tool operations. While the blast radius is limited to a single canvas drawing (not system-critical), the destructive nature of permanent removal and the lack of undo capability elevates this above Execute or Write. Confidence is high because the intent is unambiguous.
From the tool's definition Tool name is 'delete_shape' and description states 'Delete shapes by id' — this permanently removes data from the canvas without reversibility.
Documented attack patterns abuse exactly the kind of access delete_shape gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tl Draw, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_shape:
{
"version": "1",
"default": "deny",
"hide": [
"delete_shape"
]
}delete_shape disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete shapes by id. It is categorised as a Destructive tool in the Tl Draw MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tl Draw MCP server in PolicyLayer and add a rule for delete_shape: 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 Tl Draw. Nothing to install.
delete_shape 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_shape 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_shape. 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_shape is provided by the Tl Draw MCP server (siddharth11roy/tldraw-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tl Draw, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Tl Draw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.