[Agents] Reboot agents.
AI agents invoke agents_reboot to trigger actions in CyPerf MCP Server. 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 agents is an Execute-category action that triggers an external operation (system restart) on potentially multiple network testing agents. While not permanently destructive (data is not deleted), it disrupts ongoing tests and agent availability, making misuse high severity. The blast radius is high as it could interrupt active performance/security tests across the infrastructure.
From the tool's definition 'Reboot agents' — triggers a reboot operation on network test agents, which is an external operational action with significant impact
Attacks that exploit this kind of access
[Agents] Reboot agents. It is categorised as a Execute tool in the CyPerf MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CyPerf MCP Server MCP server in PolicyLayer and add a rule for agents_reboot: 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 CyPerf MCP Server. Nothing to install.
agents_reboot 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 agents_reboot 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 agents_reboot. 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.
agents_reboot is provided by the CyPerf MCP Server MCP server (keysight/cyperf-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 →