This record as markdown: /tools/hybridlabor-api-aos/setup-face-tracking.md
What setup_face_tracking does on Aos
AI agents invoke setup_face_tracking 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 setup_face_tracking is rated High
This tool executes a multi-step setup operation: it loads the MediaPipe ENGINE, accesses the system webcam (a hardware/OS-level resource), and establishes a live face-landmark tracking pipeline. It is not a simple read or write — it triggers external operations and runtime processes. Misuse could activate surveillance-like capabilities or consume system resources unexpectedly, warranting high severity.
From the tool's definition 'One-shot face-landmark tracking from a webcam: loads the MediaPipe ENGINE' — triggers an external operation that loads an engine, accesses webcam hardware, and sets up a live tracking pipeline in TouchDesigner
Attacks that exploit this kind of access
The rule that runs setup_face_tracking 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 setup_face_tracking, this is the rule to start with:
setup_face_tracking 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 setup_face_tracking call is checked against it from then on.
Questions about setup_face_tracking
One-shot face-landmark tracking from a webcam: loads the MediaPipe ENGINE (install first with. 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 setup_face_tracking: 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.
setup_face_tracking 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 setup_face_tracking 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 setup_face_tracking. 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.
setup_face_tracking 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