This record as markdown: /tools/jjpxdev-unreal-mcp/stop-trace.md
What stop_trace does on Unreal
AI agents invoke stop_trace to trigger actions in Unreal. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why stop_trace is rated High
This tool triggers an operation that stops a live trace session in Unreal Engine's profiling infrastructure. While not permanently destructive (the trace data already collected typically persists), it executes a command that halts an ongoing external process. This is an Execute action rather than Read (it modifies system state) or Destructive (the action is reversible—a new trace can be started).
From the tool's definition 'Stop the active Unreal Insights trace session' - this terminates an active tracing operation, which is an externally-observable action that affects the state of a running profiling/debugging system.
Attacks that exploit this kind of access
The rule that runs stop_trace safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Unreal, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stop_trace, this is the rule to start with:
stop_trace stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Unreal, apply this rule, and every stop_trace call is checked against it from then on.
Questions about stop_trace
Stop the active Unreal Insights trace session. It is categorised as a Execute tool in the Unreal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Unreal MCP server in PolicyLayer and add a rule for stop_trace: 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.
stop_trace 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 stop_trace 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 stop_trace. 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.
stop_trace is provided by the Unreal MCP server (@jjpxdev/unreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Unreal, and thousands of servers like it.
Across the catalogue