AI agents call stop_electron_main_cpu_profile to retrieve information from Electron without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool stops an already-running CPU profiler and retrieves the collected profile data. The primary action is returning/reading profiling data. While it does stop an ongoing operation, stopping a profiler is not destructive or irreversible — it simply ends data collection and returns results. The net effect is reading diagnostic/performance data.
From the tool's definition Stop CPU profiling and return profile data
Attacks that exploit this kind of access
Stop CPU profiling and return profile data. It is categorised as a Read tool in the Electron MCP Server, which means it retrieves data without modifying state.
Register the Electron MCP server in PolicyLayer and add a rule for stop_electron_main_cpu_profile: 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 Electron. Nothing to install.
stop_electron_main_cpu_profile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the stop_electron_main_cpu_profile 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_electron_main_cpu_profile. 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_electron_main_cpu_profile is provided by the Electron MCP server (ohah/electron-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →