Remove a specific representation (by its index) from a molecule.
AI agents call delete_representation to permanently remove resources in Vmd — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes a representation from a molecule. This is an irreversible deletion action — once removed, the representation configuration is lost and cannot be undone without recreating it manually. It fits the Destructive category due to its irreversible nature, though the blast radius is medium since it only affects visual representations rather than the underlying molecular data.
From the tool's definition Remove a specific representation (by its index) from a molecule
Attacks that exploit this kind of access
Remove a specific representation (by its index) from a molecule. It is categorised as a Destructive tool in the Vmd MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vmd MCP server in PolicyLayer and add a rule for delete_representation: 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 Vmd. Nothing to install.
delete_representation 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 delete_representation 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 delete_representation. 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.
delete_representation is provided by the Vmd MCP server (omararias-gaguancela/vmd-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 →