AI agents invoke system_automation to trigger actions in Automator. 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.
system_automation triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Perform system-level automation tasks. It is categorised as a Execute tool in the Automator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Automator MCP server in PolicyLayer and add a rule for system_automation: 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 Automator. Nothing to install.
system_automation 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 system_automation 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 system_automation. 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.
system_automation is provided by the Automator MCP server (vetcoders/automator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.