Delete atoms or residues matching the spec.
AI agents call delete_atoms to permanently remove resources in ChimeraX MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting atoms or residues from a protein structure cannot be undone within the tool's semantics and permanently alters the structural data. This is an irreversible operation that destroys information, fitting the Destructive category. Severity is high because an AI agent given broad atom selection criteria could corrupt scientific models or analysis.
From the tool's definition Tool name is 'delete_atoms' and description states 'Delete atoms or residues matching the spec' — the verb 'delete' indicates irreversible removal of data from the protein structure model.
Attacks that exploit this kind of access
Delete atoms or residues matching the spec. It is categorised as a Destructive tool in the ChimeraX MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ChimeraX MCP Server MCP server in PolicyLayer and add a rule for delete_atoms: 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 ChimeraX MCP Server. Nothing to install.
delete_atoms 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_atoms 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_atoms. 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_atoms is provided by the ChimeraX MCP Server MCP server (mahynotch/chimerax-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 →