Close one or all open models.
AI agents use close_structure to create or update resources in ChimeraX MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ChimeraX MCP Server environment.
Closing a model in ChimeraX is a reversible action—the underlying structure file remains intact and can be reopened. This is a modification of application state (the set of loaded models) rather than data deletion or destruction. It does not trigger code execution, financial operations, or irreversible data loss.
From the tool's definition Tool description states 'Close one or all open models', which removes or unloads visualization state from ChimeraX without permanently deleting underlying data files.
Attacks that exploit this kind of access
Close one or all open models. It is categorised as a Write tool in the ChimeraX MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ChimeraX MCP Server MCP server in PolicyLayer and add a rule for close_structure: 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.
close_structure is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the close_structure 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 close_structure. 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.
close_structure 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 →