manage_service · Systems Manager MCP: Risk & Policy

WHAT IT DOES

What manage_service does on Systems Manager

AI agents invoke manage_service to trigger actions in Systems Manager. 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 manage_service needs a policy

'manage_service' strongly implies controlling system services (start, stop, restart, enable, disable), which are Execute-level operations with high blast radius — stopping critical services can cause outages. The sibling tool 'list_services' (Read) suggests this tool is the action counterpart. Empty description lowers confidence, but the name and server context point clearly to Execute.

From the tool's definition Tool name 'manage_service' on a server described as enabling management of 'system updates, application installations, and remote host orchestration'; description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_service Rate-limited

manage_service 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": {
    "manage_service": {
      "limits": [
        {
          "counter": "manage_service_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 Systems Manager, so you can run agents against it safely.

FAQ

Questions about manage_service

What does the manage_service tool do? +

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

How do I enforce a policy on manage_service? +

Register the Systems Manager MCP server in PolicyLayer and add a rule for manage_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 Systems Manager. Nothing to install.

What risk level is manage_service? +

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

Can I rate-limit manage_service? +

Yes. Add a rate_limit block to the manage_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.

How do I block manage_service completely? +

Set action: deny in the PolicyLayer policy for manage_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.

What MCP server provides manage_service? +

manage_service is provided by the Systems Manager MCP server (knuckles-team/systems-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.