AI agents use set_representation to create or update resources in Vmd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vmd environment.
set_representation creates or modifies visual representations in VMD2 without deleting underlying data or executing arbitrary code. The change is reversible (another representation can be set), making it Write rather than Destructive. While it operates in a scientific visualization context, the core action is data modification.
From the tool's definition Tool description states 'Replace all visual representations of a molecule with a single new one' — this modifies the visual state of loaded molecular structures. It is a reversible change to representation parameters.
Attacks that exploit this kind of access
Replace all visual representations of a molecule with a single new one. It is categorised as a Write tool in the Vmd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vmd MCP server in PolicyLayer and add a rule for set_representation: 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.
set_representation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_representation 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 set_representation. 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.
set_representation 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 →