AI agents invoke voice 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.
Toggling voice is an external action within the VRChat environment that changes the state of the user's microphone/voice output. It is not a simple read or reversible data write, but rather an operation that triggers a real-time change in a live virtual environment. It could affect ongoing social interactions (e.g., unmuting during a private conversation), giving it medium severity.
From the tool's definition Toggle voice — triggers an external operation (toggling voice/microphone state) in a VRChat environment via OSC
Documented attack patterns abuse exactly the kind of access voice 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 voice:
{
"version": "1",
"default": "deny",
"tools": {
"voice": {
"limits": [
{
"counter": "voice_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}voice 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.
Toggle voice. 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 voice: 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.
voice 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 voice 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 voice. 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.
voice 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.