load_trajectory · Vmd MCP: Risk & Policy

WHAT IT DOES

What load_trajectory does on Vmd

AI agents use load_trajectory 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.

WHY IT NEEDS A POLICY

Why load_trajectory needs a policy

This tool loads data into the VMD application, creating new molecular objects/state within the session. It is a write operation (importing/creating data in the application context) rather than a read (it modifies application state) or execute (it doesn't run arbitrary code). Misuse could load malformed or very large trajectory files causing resource exhaustion, hence medium severity.

From the tool's definition Load a topology file together with a trajectory (DCD, XTC, TRR, etc.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

load_trajectory Rate-limited

load_trajectory stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "load_trajectory": {
      "limits": [
        {
          "counter": "load_trajectory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Vmd, so you can run agents against it safely.

FAQ

Questions about load_trajectory

What does the load_trajectory tool do? +

Load a topology file together with a trajectory (DCD, XTC, TRR, etc.). 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.

How do I enforce a policy on load_trajectory? +

Register the Vmd MCP server in PolicyLayer and add a rule for load_trajectory: 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.

What risk level is load_trajectory? +

load_trajectory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit load_trajectory? +

Yes. Add a rate_limit block to the load_trajectory 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.

How do I block load_trajectory completely? +

Set action: deny in the PolicyLayer policy for load_trajectory. 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.

What MCP server provides load_trajectory? +

load_trajectory 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.