Operations for managing system services
AI agents invoke sm_service_operations 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.
Managing system services involves starting, stopping, restarting, enabling, or disabling services on a host. These are external system operations with real side effects (e.g., stopping a critical service causes downtime), placing this firmly in Execute. The sibling tool 'manage_service' confirms the pattern. Misuse could disrupt critical infrastructure, warranting high severity.
From the tool's definition 'Operations for managing system services' combined with server context 'manage system updates, application installations, and remote host orchestration'
Attacks that exploit this kind of access
Operations for managing system services. 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.
Register the Systems Manager MCP server in PolicyLayer and add a rule for sm_service_operations: 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.
sm_service_operations 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 sm_service_operations 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 sm_service_operations. 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.
sm_service_operations 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.
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 →