AI agents call get_cpu_governor to retrieve information from Sysprobe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only diagnostic tool that queries system state without side effects. It returns information about CPU governor settings but does not change them. The 'safety model that requires explicit flags for mutating actions' reinforces that this non-flagged tool is non-mutating.
From the tool's definition Tool retrieves current CPU frequency governor and available options. No modification occurs; the description uses only passive language ('Current...the ones available') without any mutating verbs.
Attacks that exploit this kind of access
Current CPU frequency governor + the ones available. It is categorised as a Read tool in the Sysprobe MCP Server, which means it retrieves data without modifying state.
Register the Sysprobe MCP server in PolicyLayer and add a rule for get_cpu_governor: 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 Sysprobe. Nothing to install.
get_cpu_governor 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 get_cpu_governor 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 get_cpu_governor. 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.
get_cpu_governor is provided by the Sysprobe MCP server (raindancer118/sysprobe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_cpu_governor is one line of Sysprobe's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →