AI agents use td_create_op to create or update resources in Td — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Td environment.
Creating operators in TouchDesigner modifies the project state reversibly (operators can be deleted). This is a Write action rather than Execute, as it creates structure rather than running arbitrary code. However, it carries high severity because malicious operator chains could be created to exfiltrate data or degrade system performance.
From the tool's definition Tool name 'td_create_op' combined with server context of 'controlling TouchDesigner' and 'operator manipulation' indicates creation of new operators within a visual programming environment.
Attacks that exploit this kind of access
td_create_op. It is categorised as a Write tool in the Td MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Td MCP server in PolicyLayer and add a rule for td_create_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_create_op is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the td_create_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_create_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_create_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 →