Remove an element from the DOM
AI agents call dom_remove to permanently remove resources in Claude Imagine — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a DOM element is a destructive operation as it irreversibly deletes that element and its children from the live document. While a page reload could restore it, within the context of a running session the action cannot be undone. The blast radius is medium since it affects the rendered UI but not persistent data or financial systems.
From the tool's definition 'Remove an element from the DOM' — permanently removes a UI element, which is irreversible within the current DOM state
Attacks that exploit this kind of access
Remove an element from the DOM. It is categorised as a Destructive tool in the Claude Imagine MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Imagine MCP server in PolicyLayer and add a rule for dom_remove: 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 Claude Imagine. Nothing to install.
dom_remove 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 dom_remove 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 dom_remove. 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.
dom_remove is provided by the Claude Imagine MCP server (t3rm1nu55/claudeimagine). 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 →