AI agents invoke control_service to trigger actions in Sysprobe. 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.
Systemd service control operations are executable actions that trigger real changes to system services and their startup behavior. While not destructive (services can be restarted), they execute commands whose outcomes depend on arguments and could disrupt system functionality or cause denial of service if misconfigured.
From the tool's definition Tool performs [ACTION] to 'start/stop/restart/reload/enable/disable a systemd unit' — these are operational commands that trigger external system-level service control operations whose effects depend on which service and action are specified.
Attacks that exploit this kind of access
[ACTION] start/stop/restart/reload/enable/disable a systemd unit. It is categorised as a Execute tool in the Sysprobe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sysprobe MCP server in PolicyLayer and add a rule for control_service: 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.
control_service 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 control_service 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 control_service. 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.
control_service 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.
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 →