This record as markdown: /tools/coolify/stop-service.md
What stop_service does on Coolify
AI agents invoke stop_service to trigger actions in Coolify. 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 stop_service is rated High
Stopping a service is an operational action that triggers external effects (service termination) whose consequences depend on which service is targeted. It is not a simple data read, and while it can theoretically be reversed by restarting the service, the primary action is an immediate state-changing operation.
From the tool's definition Tool name is 'stop_service' and description states 'Stop a service.' This action executes a command to halt a running service, which has immediate operational effects on system state and availability.
Attacks that exploit this kind of access
The rule that runs stop_service safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Coolify, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stop_service, this is the rule to start with:
stop_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Coolify, apply this rule, and every stop_service call is checked against it from then on.
Questions about stop_service
Stop a service. It is categorised as a Execute tool in the Coolify MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Coolify MCP server in PolicyLayer and add a rule for stop_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 Coolify. Nothing to install.
stop_service 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 stop_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.
Set action: deny in the PolicyLayer policy for stop_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.
stop_service is provided by the Coolify MCP server (coolify-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Coolify, and thousands of servers like it.
Across the catalogue