restart_server · Model Radar MCP: Risk & Policy

WHAT IT DOES

What restart_server does on Model Radar

AI agents invoke restart_server to trigger actions in Model Radar. 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.

WHY IT NEEDS A POLICY

Why restart_server needs a policy

Restarting a server is an Execute action—it runs a system-level operation with effects that depend on system state (which services are running, connections active, etc.). While not Destructive (restart is reversible), it disrupts service availability and could cascade to dependent processes. High severity due to potential disruption to AI agent operations relying on continuous model availability.

From the tool's definition Tool name 'restart_server' indicates server restart capability; combined with server context involving 130+ model pings and real-time operations, this triggers external operational changes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

restart_server Rate-limited

restart_server stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "restart_server": {
      "limits": [
        {
          "counter": "restart_server_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Model Radar, so you can run agents against it safely.

FAQ

Questions about restart_server

What does the restart_server tool do? +

restart_server. It is categorised as a Execute tool in the Model Radar MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on restart_server? +

Register the Model Radar MCP server in PolicyLayer and add a rule for restart_server: 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 Model Radar. Nothing to install.

What risk level is restart_server? +

restart_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit restart_server? +

Yes. Add a rate_limit block to the restart_server 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.

How do I block restart_server completely? +

Set action: deny in the PolicyLayer policy for restart_server. 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.

What MCP server provides restart_server? +

restart_server is provided by the Model Radar MCP server (srclight/model-radar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.