Select all atoms within N Angstroms of a selection.
AI agents call select_near to retrieve information from ChimeraX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a selection operation — identifying and marking atoms based on spatial proximity. Selection in molecular visualization tools like ChimeraX is a non-destructive, read-like operation that queries geometric relationships without modifying, deleting, or executing anything. It does not alter structure data, only the current selection state, which is reversible and has minimal blast radius.
From the tool's definition Select all atoms within N Angstroms of a selection
Attacks that exploit this kind of access
Select all atoms within N Angstroms of a selection. It is categorised as a Read tool in the ChimeraX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ChimeraX MCP Server MCP server in PolicyLayer and add a rule for select_near: 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.
select_near is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the select_near 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 select_near. 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.
select_near 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 →