AI agents invoke dokploy_deploy 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 tool triggers deployment operations, which execute application code and infrastructure changes in live environments. While not immediately destructive (prior code/config must exist), deployments have significant blast radius through service interruptions, resource consumption, or bugs introduced in the deployed code.
From the tool's definition Tool description states 'Trigger a deployment for an application' — deployments execute code and external operations in production environments whose effects depend on which application is targeted and the deployment configuration.
Attacks that exploit this kind of access
Trigger a deployment for an 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_deploy: 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_deploy 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_deploy 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_deploy. 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_deploy 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 →