AI agents invoke look_direction to trigger actions in VRChat MCP OSC. 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.
This tool executes a real-time action in an external VR environment (VRChat), controlling avatar orientation via OSC protocol. It is not a simple data read or write, but an action that triggers an external operation whose effects depend on the direction argument provided. The blast radius is medium as it affects avatar behavior in a live VR session.
From the tool's definition 'Turn to look in a specific direction' — triggers an external operation (avatar movement/rotation in VRChat via OSC)
Documented attack patterns abuse exactly the kind of access look_direction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VRChat MCP OSC, and nothing reaches the server without passing your rules. This is the rule we recommend for look_direction:
{
"version": "1",
"default": "deny",
"tools": {
"look_direction": {
"limits": [
{
"counter": "look_direction_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}look_direction 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.
Free to start. No card required.
Turn to look in a specific direction. It is categorised as a Execute tool in the VRChat MCP OSC MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VRChat MCP OSC MCP server in PolicyLayer and add a rule for look_direction: 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 VRChat MCP OSC. Nothing to install.
look_direction 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 look_direction 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 look_direction. 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.
look_direction is provided by the VRChat MCP OSC MCP server (krekun/vrchat-mcp-osc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VRChat MCP OSC, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 VRChat MCP OSC tools catalogued and risk-classified — across an index of 43,000+ MCP servers.