Reboots the MikroTik device (requires confirmation)
AI agents invoke mikrotik_reboot_system to trigger actions in MikroTik Cursor MCP. 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.
Rebooting a router triggers an external operation (system restart) that causes temporary network outage and interrupts all active connections. It is not destructive (data is not deleted) nor financial, but it executes a privileged system action with significant blast radius — misuse could disrupt an entire network.
From the tool's definition Reboots the MikroTik device
Attacks that exploit this kind of access
Reboots the MikroTik device (requires confirmation). It is categorised as a Execute tool in the MikroTik Cursor MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MikroTik Cursor MCP server in PolicyLayer and add a rule for mikrotik_reboot_system: 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 MikroTik Cursor MCP. Nothing to install.
mikrotik_reboot_system 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 mikrotik_reboot_system 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 mikrotik_reboot_system. 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.
mikrotik_reboot_system is provided by the MikroTik Cursor MCP server (kevinpez/mikrotik-cursor-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 →