Remove a molecule from VMD by its molecule ID.
AI agents call delete_molecule 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.
This tool permanently removes data (a loaded molecular structure) from VMD with no undo mechanism. While the original file remains, the in-memory representation and all associated analyses are lost. This is irreversible within the session, making it Destructive rather than Write.
From the tool's definition delete_molecule - 'Remove a molecule from VMD by its molecule ID' irreversibly deletes loaded molecular structures from the visualization environment.
Attacks that exploit this kind of access
Remove a molecule from VMD by its molecule ID. 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_molecule: 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_molecule 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_molecule 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_molecule. 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_molecule 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 →