Control the project runtime: profiling, benchmarks, scalability/LOD/Nanite settings, CVars, console commands, Python scripts, UBT, tests, logs, and widgets. Required: action. Select one enum value, then provide only parameters relevant to that action. Params by action: profileType, category, leve...
Risk signalsAccepts freeform code/query input (command) · Accepts file system path (file) · High parameter count (59 properties) · Admin/system-level operation
Part of the Unreal Engine server.
Free to start. No card required.
AI agents invoke system_control to trigger processes or run actions in Unreal Engine. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
system_control can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"system_control": {
"limits": [
{
"counter": "system_control_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Unreal Engine policy for all 23 tools.
These attack patterns abuse exactly the kind of access system_control gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Control the project runtime: profiling, benchmarks, scalability/LOD/Nanite settings, CVars, console commands, Python scripts, UBT, tests, logs, and widgets. Required: action. Select one enum value, then provide only parameters relevant to that action. Params by action: profileType, category, level, enabled, resolution, command, target, platform, configuration, arguments, filter, channels, widgetPath, childClass, parentName, section, key, value, code, file, mode, returnBase64, includeMetadata, metadata, type, duration, outputPath, detailed, scale, maxFPS, poolSize, boostPlayerLocation, forceLOD, lodBias, enableInstancing, enableBatching, mergeActors, actors, streamingDistance, cellSize, categoryName, filename, height, message, name, packageName, assetPath, path, paths, recursive, replaceSourceActors, savePath, text, volume, widgetId, width, windowed, params.. It is categorised as a Execute tool in the Unreal Engine MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Unreal Engine MCP server in PolicyLayer and add a rule for system_control: 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 Engine. Nothing to install.
system_control is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the system_control 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 system_control. 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.
system_control is provided by the Unreal Engine MCP server (ChiR24/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 23 Unreal Engine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.