Delete an operator.
AI agents call td_delete_op to permanently remove resources in Td — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting an operator in TouchDesigner is an irreversible operation that removes the operator and its associated state from the project. This cannot be undone programmatically by the MCP tool itself (though TouchDesigner's undo may help). An AI agent given this tool could accidentally or maliciously remove critical operators from a user's project, causing data loss and workflow disruption.
From the tool's definition Tool name 'td_delete_op' combined with description 'Delete an operator' indicates irreversible removal of data/objects in the TouchDesigner environment. The word 'Delete' is a clear destructive action.
Attacks that exploit this kind of access
Delete an operator. It is categorised as a Destructive tool in the Td MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Td MCP server in PolicyLayer and add a rule for td_delete_op: 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 Td. Nothing to install.
td_delete_op 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 td_delete_op 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 td_delete_op. 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.
td_delete_op is provided by the Td MCP server (tai5863/td-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 →