system_run_command

THE RISK

High Risk

Why system_run_command needs a policy

A tool named 'system_run_command' that executes system commands represents Execute-level risk (or potentially Destructive/critical depending on what commands can be run). On a production CAD automation server integrated with AI agents, this poses extreme blast radius: attackers or misdirected agents could execute arbitrary code, modify files, exfiltrate data, or compromise the system.

From the tool's definition Tool name 'system_run_command' indicates execution of arbitrary system commands; description is empty but the name alone is a strong signal for command execution capability in an AutoCAD automation context.

Risk signalsAdmin/system-level operation

Documented attack patterns abuse exactly the kind of access system_run_command gives an agent:

POLICY

How to control system_run_command

PolicyLayer is an MCP gateway — it sits between your AI agents and AutoCAD MCP Pro, and nothing reaches the server without passing your rules. This is the rule we recommend for system_run_command:

policy.json

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

system_run_command 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.

Create a free account and register AutoCAD MCP Pro — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More AutoCAD MCP Pro tools

Destructive construction_clear Delete every entity on the CONSTRUCTION layer. Idempotent. Destructive drawing_purge Purge all unused objects (layers, blocks, linetypes, styles) from the drawing. Destructive entity_delete Permanently delete an entity by its handle. Destructive entity_delete_many Delete multiple entities in one call. Returns count of deleted entities. Destructive layer_delete layer_delete Destructive block_explode block_explode Execute drawing_audit Run an integrity audit on the drawing to detect and fix errors. Execute system_run_lisp system_run_lisp

All 108 AutoCAD MCP Pro tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in AutoCAD MCP Pro → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about system_run_command

What does the system_run_command tool do? +

system_run_command. It is categorised as a Execute tool in the AutoCAD MCP Pro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on system_run_command? +

Register the AutoCAD MCP Pro MCP server in PolicyLayer and add a rule for system_run_command: 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 AutoCAD MCP Pro. Nothing to install.

What risk level is system_run_command? +

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

Can I rate-limit system_run_command? +

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

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

system_run_command is provided by the AutoCAD MCP Pro MCP server (u-c4n/autocad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AutoCAD MCP Pro tool call.

Start from AutoCAD MCP Pro, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →