Restart the computer
AI agents invoke restart to trigger actions in Windows 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.
Restarting a computer is an Execute-class action: it runs a system command with significant side effects (all processes terminate, system goes offline temporarily). While not permanent data destruction, it's highly disruptive and could cause data loss in unsaved applications or interrupt critical services.
From the tool's definition Tool name is 'restart' with description 'Restart the computer'. This triggers a system-level operation that interrupts all running processes and services.
Attacks that exploit this kind of access
Restart the computer. It is categorised as a Execute tool in the Windows MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Windows MCP Server MCP server in PolicyLayer and add a rule for restart: 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 Windows MCP Server. Nothing to install.
restart 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 restart 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 restart. 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.
restart is provided by the Windows MCP Server MCP server (romeo2badboy-rgb/windows-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 →