AI agents use import_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.
Importing assets into a live game editor modifies project state reversibly. While the empty description reduces confidence, the name clearly indicates a Write operation (adding/creating asset entries). Severity is high because mass asset imports could corrupt project structure or consume significant resources, affecting the editor's stability.
From the tool's definition Tool name 'import_asset' indicates creation/addition of assets into the UEFN editor; no destructive deletion mentioned. Description is empty, limiting precision.
Documented attack patterns abuse exactly the kind of access import_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 import_asset:
{
"version": "1",
"default": "deny",
"tools": {
"import_asset": {
"limits": [
{
"counter": "import_asset_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}import_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.
import_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 import_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.
import_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 import_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 import_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.
import_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.