AI agents invoke reset_view 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 triggers an action in an external application (VMD2), resetting the camera and view state. It doesn't read data, write/create persistent data, delete anything, or involve finances. It's an external operation with minimal blast radius — the worst outcome is an unwanted view reset, which is easily reversible by the user.
From the tool's definition "Center all loaded molecules and reset the camera to the default view" — triggers an external operation in VMD2 (recentering and camera reset)
Attacks that exploit this kind of access
Center all loaded molecules and reset the camera to the default view. 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 reset_view: 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.
reset_view 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 reset_view 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 reset_view. 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.
reset_view 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 →