AI agents use vrchat_add_favorite to create or update resources in VRChat MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VRChat MCP Server environment.
This tool creates/adds data (a favorite) which is a Write operation. It is reversible (favorites can be removed), affects only the authenticated user's data with limited blast radius, and does not execute arbitrary code, delete irreversibly, or move money. Severity is low because favoriting is a benign user preference change with no harmful side effects.
From the tool's definition The tool 'vrchat_add_favorite' creates a new favorite entry in the user's VRChat favorites list. The description 'Add a new favorite' indicates a create operation that modifies user data reversibly.
Documented attack patterns abuse exactly the kind of access vrchat_add_favorite gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VRChat MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for vrchat_add_favorite:
{
"version": "1",
"default": "deny",
"tools": {
"vrchat_add_favorite": {
"limits": [
{
"counter": "vrchat_add_favorite_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}vrchat_add_favorite 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.
Add a new favorite. It is categorised as a Write tool in the VRChat MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VRChat MCP Server MCP server in PolicyLayer and add a rule for vrchat_add_favorite: 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 Server. Nothing to install.
vrchat_add_favorite 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 vrchat_add_favorite 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 vrchat_add_favorite. 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.
vrchat_add_favorite is provided by the VRChat MCP Server MCP server (sawa-zen/vrchat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 VRChat MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 VRChat MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.