AI agents use save_current_level to create or update resources in Unreal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unreal environment.
Saving a level file modifies the persistent state of the project on disk. While not destructive (the action is reversible through undo or version control), it is definitively a Write operation as it commits changes to stored data.
From the tool's definition Tool description states 'Save the currently open Unreal level' — this modifies and persists the level file state, making it a Write operation that creates or updates data reversibly.
Documented attack patterns abuse exactly the kind of access save_current_level gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Unreal, and nothing reaches the server without passing your rules. This is the rule we recommend for save_current_level:
{
"version": "1",
"default": "deny",
"tools": {
"save_current_level": {
"limits": [
{
"counter": "save_current_level_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_current_level 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.
Save the currently open Unreal level. It is categorised as a Write tool in the Unreal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unreal MCP server in PolicyLayer and add a rule for save_current_level: 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 Unreal. Nothing to install.
save_current_level 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 save_current_level 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 save_current_level. 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.
save_current_level is provided by the Unreal MCP server (runeape-sats/unreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Unreal tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Unreal tools catalogued and risk-classified — across an index of 42,500+ MCP servers.