execute_tcl · Vmd MCP: Risk & Policy

WHAT IT DOES

What execute_tcl does on Vmd

AI agents invoke execute_tcl 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.

WHY IT NEEDS A POLICY

Why execute_tcl needs a policy

This tool allows execution of arbitrary Tcl commands within VMD's runtime environment. While the server context is molecular dynamics analysis, the ability to execute raw Tcl grants the AI agent full programmatic control over VMD, including potential system-level operations. This is functionally equivalent to a shell execution tool.

From the tool's definition Tool name 'execute_tcl' and description 'Send a raw Tcl command directly to VMD' indicate arbitrary code execution capability. Tcl is a scripting language that can invoke system calls, modify molecular structures, delete data, and trigger external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_tcl Rate-limited

execute_tcl stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_tcl": {
      "limits": [
        {
          "counter": "execute_tcl_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 execute_tcl

What does the execute_tcl tool do? +

Send a raw Tcl command directly to VMD. 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.

How do I enforce a policy on execute_tcl? +

Register the Vmd MCP server in PolicyLayer and add a rule for execute_tcl: 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 execute_tcl? +

execute_tcl is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_tcl? +

Yes. Add a rate_limit block to the execute_tcl 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 execute_tcl completely? +

Set action: deny in the PolicyLayer policy for execute_tcl. 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 execute_tcl? +

execute_tcl 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.