AI agents invoke dokploy_stop_application to trigger actions in Dokploy. 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 is Execute rather than Write because it triggers an external operational action (stopping a service) whose effects are immediate and depend on which application is targeted. While not destructive (the application data persists and can be restarted), it causes a service interruption and is more impactful than data modification.
From the tool's definition The tool "stops a running application" - this triggers an operational state change on an external system (Dokploy-managed infrastructure). Stopping an application is a control plane action that immediately affects running services.
Attacks that exploit this kind of access
Stop a running application. It is categorised as a Execute tool in the Dokploy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dokploy MCP server in PolicyLayer and add a rule for dokploy_stop_application: 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 Dokploy. Nothing to install.
dokploy_stop_application 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 dokploy_stop_application 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 dokploy_stop_application. 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.
dokploy_stop_application is provided by the Dokploy MCP server (wyattjoh/dokploy-mcp). 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 →