AI agents use rename_asset to create or update resources in Uefn — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Uefn environment.
Renaming assets in a game editor is a write operation—it modifies metadata reversibly. While not destructive (the original asset still exists under a new name), it can have broad side effects on project references and workflows. High severity because an AI agent could systematically rename critical assets, breaking references or creating confusion in a live UEFN project.
From the tool's definition Tool name 'rename_asset' indicates modification of asset metadata. In Unreal Editor for Fortnite, renaming assets changes their identity and references throughout a project, making this a reversible write operation.
Documented attack patterns abuse exactly the kind of access rename_asset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Uefn, and nothing reaches the server without passing your rules. This is the rule we recommend for rename_asset:
{
"version": "1",
"default": "deny",
"tools": {
"rename_asset": {
"limits": [
{
"counter": "rename_asset_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}rename_asset 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.
rename_asset. It is categorised as a Write tool in the Uefn MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Uefn MCP server in PolicyLayer and add a rule for rename_asset: 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 Uefn. Nothing to install.
rename_asset 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 rename_asset 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 rename_asset. 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.
rename_asset is provided by the Uefn MCP server (quangdang46/uefn-verse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Uefn, 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.
143 Uefn tools catalogued and risk-classified — across an index of 43,000+ MCP servers.