Remove all labels.
AI agents call clear_labels 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.
The tool removes all labels from the visualization, which is a bulk, potentially irreversible action. While labels themselves are not critical data (they can often be recreated), 'remove all' with no mention of reversibility places this in the Destructive category. Severity is medium because labels are derived/display data rather than primary structural data, so the blast radius is limited.
From the tool's definition 'Remove all labels' — the word 'remove' and 'all' indicate an irreversible bulk deletion operation with no indication of undo capability.
Attacks that exploit this kind of access
Remove all labels. 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 clear_labels: 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.
clear_labels 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 clear_labels 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 clear_labels. 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.
clear_labels 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 →