create_visual_system
Create a complete visual system from a natural-language description. Classifies intent (audio-reactive, particle, feedback, reaction-diffusion, landscape, generative) and delegates to the matching Layer-1 builder (or a tag-matched recipe), creating a self-contained COMP under parent_path, then ve...
This record as markdown: /tools/hybridlabor-api-aos/create-visual-system.md
What create_visual_system does on Aos
AI agents invoke create_visual_system to trigger actions in Aos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why create_visual_system is rated High
This tool triggers complex external operations in TouchDesigner — building network nodes, instantiating components, executing builder logic, and launching previews — based on arbitrary natural-language input. The effects depend heavily on arguments (the description and parent_path), and the tool orchestrates multiple sub-operations including classification, delegation, construction, verification, and preview.
From the tool's definition 'Create a complete visual system from a natural-language description... delegates to the matching Layer-1 builder (or a tag-matched recipe), creating a self-contained COMP under parent_path, then verifies and previews it'
Attacks that exploit this kind of access
The rule that runs create_visual_system 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 create_visual_system, this is the rule to start with:
create_visual_system stays usable, but rate-capped: a runaway agent can't fire it dozens of times 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 create_visual_system call is checked against it from then on.
Questions about create_visual_system
Create a complete visual system from a natural-language description. Classifies intent (audio-reactive, particle, feedback, reaction-diffusion, landscape, generative) and delegates to the matching Layer-1 builder (or a tag-matched recipe), creating a self-contained COMP under parent_path, then verifies and previews it. Use plan_visual instead for a dry run that reports which tool/recipe would be chosen without building anything. Returns a note on how the description was interpreted plus the underlying builder. It is categorised as a Execute tool in the Aos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Aos MCP server in PolicyLayer and add a rule for create_visual_system: 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.
create_visual_system is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_visual_system 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 create_visual_system. 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.
create_visual_system 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