Create application from Dockerfile
AI agents use create_dockerfile_application to create or update resources in Coolify MCP Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Coolify MCP Tools environment.
This tool creates a new application resource from a Dockerfile specification. While creation is reversible (the application can be deleted), it directly deploys containerized code into managed infrastructure, which could instantiate malicious applications or drain resources.
From the tool's definition Tool name 'create_dockerfile_application' and description 'Create application from Dockerfile' indicate creation of infrastructure/application resources.
Attacks that exploit this kind of access
Create application from Dockerfile. It is categorised as a Write tool in the Coolify MCP Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Coolify MCP Tools MCP server in PolicyLayer and add a rule for create_dockerfile_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 Coolify MCP Tools. Nothing to install.
create_dockerfile_application is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_dockerfile_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 create_dockerfile_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.
create_dockerfile_application is provided by the Coolify MCP Tools MCP server (jplansink/coolify-mcp-tools). 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 →