create_pose_controlnet_driver
Render a canonical OpenPose-colored stick figure TOP (per-limb RGB lines + per-joint colored discs on a black background, default 512×512) from an existing pose CHOP produced by create_pose_tracking. The render is GPU-rasterized in a single GLSL TOP that samples the pose CHOP via a CHOP-to-TOP. O...
This record as markdown: /tools/hybridlabor-api-aos/create-pose-controlnet-driver.md
What create_pose_controlnet_driver does on Aos
AI agents use create_pose_controlnet_driver 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 create_pose_controlnet_driver is rated Medium
This tool creates new nodes/operators in TouchDesigner (a GLSL TOP, CHOP-to-TOP conversion, optional sender wiring) and produces a rendered output image. It is primarily a Write/create operation — it builds and wires components in the TD network. It does not delete anything, execute arbitrary code, or involve financial transactions.
From the tool's definition 'Render a canonical OpenPose-colored stick figure TOP... from an existing pose CHOP', 'Optionally auto-wires the output to a Syphon/Spout or NDI sender', 'this tool produces the driver conditioning image that ControlNet consumes'
Attacks that exploit this kind of access
The rule that runs create_pose_controlnet_driver 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_pose_controlnet_driver, this is the rule to start with:
create_pose_controlnet_driver 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 create_pose_controlnet_driver call is checked against it from then on.
Questions about create_pose_controlnet_driver
Render a canonical OpenPose-colored stick figure TOP (per-limb RGB lines + per-joint colored discs on a black background, default 512×512) from an existing pose CHOP produced by create_pose_tracking. The render is GPU-rasterized in a single GLSL TOP that samples the pose CHOP via a CHOP-to-TOP. Optionally auto-wires the output to a Syphon/Spout or NDI sender for a downstream Stable Diffusion / ComfyUI / StreamDiffusion ControlNet node. No model inference — this tool produces the driver conditioning image that ControlNet consumes. 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 create_pose_controlnet_driver: 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_pose_controlnet_driver 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 create_pose_controlnet_driver 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_pose_controlnet_driver. 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_pose_controlnet_driver 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