AI agents use set_avatar to create or update resources in VRChat MCP OSC — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VRChat MCP OSC environment.
This tool changes/updates which avatar is active, which is a reversible modification of user state. It doesn't delete data, execute arbitrary code, or involve finances. It is a Write operation since the avatar can be changed back. Severity is medium because misuse could disrupt a user's VRChat session or impersonate different personas, but it is generally reversible.
From the tool's definition "Change to a specific avatar" — modifies the current avatar state in VRChat
Documented attack patterns abuse exactly the kind of access set_avatar 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 set_avatar:
{
"version": "1",
"default": "deny",
"tools": {
"set_avatar": {
"limits": [
{
"counter": "set_avatar_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_avatar 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.
Free to start. No card required.
Change to a specific avatar. It is categorised as a Write tool in the VRChat MCP OSC MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VRChat MCP OSC MCP server in PolicyLayer and add a rule for set_avatar: 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.
set_avatar 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 set_avatar 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 set_avatar. 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.
set_avatar 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.