This record as markdown: /tools/hybridlabor-api-aos/randomize-controls.md
What randomize_controls does on Aos
AI agents use randomize_controls to create or update resources in Aos, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Aos environment.
Why randomize_controls is rated Medium
Randomizing a COMP involves writing new parameter values to a TouchDesigner component. This is a reversible modification (parameters can be reset or changed again), placing it in the Write category. The blast radius is medium since misuse could disrupt a live visual system, but the action is not irreversible.
From the tool's definition 'Randomize a COMP' — modifies component parameters by setting them to random values
Attacks that exploit this kind of access
The rule that runs randomize_controls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For randomize_controls, this is the rule to start with:
randomize_controls stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Aos, apply this rule, and every randomize_controls call is checked against it from then on.
Questions about randomize_controls
Randomize a COMP. It is categorised as a Write tool in the Aos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Aos MCP server in PolicyLayer and add a rule for randomize_controls: 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 Aos. Nothing to install.
randomize_controls 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 randomize_controls 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 randomize_controls. 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.
randomize_controls is provided by the Aos MCP server (@hybridlabor-api/aos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aos, and thousands of servers like it.
This server
Across the catalogue