Stop ETW trace, run tracerpt to CSV and summary, return parsed preview (requires elevation).
AI agents invoke stop_etw_trace to trigger actions in Procmon. 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.
This tool executes external commands (tracerpt) and manipulates system trace state by stopping ETW (Event Tracing for Windows) traces. While not destructive in the sense of data deletion, it executes arbitrary operations on system internals that depend on runtime arguments and state.
From the tool's definition Tool description explicitly states 'Stop ETW trace, run tracerpt' — this involves executing a command (tracerpt) and terminating system tracing. The 'requires elevation' note indicates this performs privileged system operations.
Documented attack patterns abuse exactly the kind of access stop_etw_trace gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Procmon, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_etw_trace:
{
"version": "1",
"default": "deny",
"tools": {
"stop_etw_trace": {
"limits": [
{
"counter": "stop_etw_trace_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} stop_etw_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.
Free to start. No card required.
Stop ETW trace, run tracerpt to CSV and summary, return parsed preview (requires elevation). It is categorised as a Execute tool in the Procmon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Procmon MCP server in PolicyLayer and add a rule for stop_etw_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 Procmon. Nothing to install.
stop_etw_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_etw_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_etw_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_etw_trace is provided by the Procmon MCP server (0xhackerfren/procmon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Procmon tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 Procmon tools catalogued and risk-classified — across an index of 42,500+ MCP servers.