Remove unused images
AI agents call prune_images to permanently remove resources in Docker MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Pruning Docker images deletes image layers and data that cannot be recovered without rebuilding or re-pulling. This is an irreversible operation that destroys data, fitting the Destructive category. Severity is high because unintended mass deletion of images could significantly disrupt containerized operations and require time-consuming recovery (re-pulling images).
From the tool's definition Tool name 'prune_images' combined with description 'Remove unused images' indicates irreversible deletion of Docker image data. The word 'Remove' in the description confirms destructive intent.
Attacks that exploit this kind of access
Remove unused images. It is categorised as a Destructive tool in the Docker MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Docker MCP Server MCP server in PolicyLayer and add a rule for prune_images: 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 Docker MCP Server. Nothing to install.
prune_images is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the prune_images 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 prune_images. 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.
prune_images is provided by the Docker MCP Server MCP server (swartdraak/docker-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 →