Start a service
AI agents invoke start_service to trigger actions in Coolify MCP Server. 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.
This tool triggers operational state changes on running services, which is an external operation execution. While not destructive (the service can be stopped), it is an Execute-class action because it initiates processes/services whose side effects depend on runtime context and arguments.
From the tool's definition Tool name 'start_service' combined with server description indicating ability to 'control applications, databases, and servers' and 'deploying services' demonstrates triggering of external operations.
Attacks that exploit this kind of access
Start a service. It is categorised as a Execute tool in the Coolify MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Coolify MCP Server MCP server in PolicyLayer and add a rule for start_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 MCP Server. Nothing to install.
start_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 start_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 start_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.
start_service is provided by the Coolify MCP Server MCP server (joshuarileydev/coolify-mcp-server). 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 →