AI agents call measure_angle 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.
This tool retrieves and computes a geometric property from already-loaded molecular structures without creating, modifying, deleting, or executing any side effects. It is analogous to a query operation on molecular data. The severity is low because misuse (e.g., measuring wrong atoms) produces only incorrect output with no operational consequences.
From the tool's definition Tool description states it 'Measure[s] the angle in degrees formed by three atoms' — a pure data retrieval operation with no modification or execution of external commands. Takes atom indices as input and returns a calculated angle value.
Attacks that exploit this kind of access
Measure the angle in degrees formed by three atoms (specified by atom indices). 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_angle: 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_angle 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_angle 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_angle. 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_angle 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 →