AI agents invoke go_to_frame to trigger actions in Vmd. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool changes the current frame of a trajectory in the running VMD application. It is not a passive read (it modifies application state), not a write to persistent data, and not destructive or financial. It executes an operation that alters the VMD session state, similar to a UI action/trigger, placing it in the Execute category.
From the tool's definition 'Jump the trajectory of a molecule to a specific frame number' — triggers a state change in the VMD application, navigating playback position
Attacks that exploit this kind of access
Jump the trajectory of a molecule to a specific frame number. It is categorised as a Execute tool in the Vmd MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vmd MCP server in PolicyLayer and add a rule for go_to_frame: 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.
go_to_frame is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the go_to_frame 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 go_to_frame. 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.
go_to_frame 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 →