AI agents call measure_rmsd to retrieve information from Vmd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
RMSD is a metric calculation that queries molecular structure data to produce an analytical result. It does not create, modify, delete, execute arbitrary code, or trigger external operations. While the server includes execute_tcl (Execute category) and delete_* tools (Destructive category), measure_rmsd itself is purely analytical.
From the tool's definition measure_rmsd computes RMSD (root mean square deviation) for molecular dynamics analysis. The verb 'compute' and the read-only nature of RMSD calculation—which analyzes existing molecular structure data without modifying it—indicates a retrieval/analysis…
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Compute the RMSD (root mean square deviation) in Ångströms for a given. It is categorised as a Read tool in the Vmd MCP Server, which means it retrieves data without modifying state.
Register the Vmd MCP server in PolicyLayer and add a rule for measure_rmsd: 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.
measure_rmsd 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 measure_rmsd 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 measure_rmsd. 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.
measure_rmsd 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 →