run_cmd_tool · Windows Operations MCP: Risk & Policy

WHAT IT DOES

What run_cmd_tool does on Windows Operations MCP

AI agents invoke run_cmd_tool to trigger actions in Windows Operations MCP. 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 run_cmd_tool needs a policy

This tool allows execution of arbitrary Windows CMD commands, which can perform any operation an attacker instructs—from data exfiltration to system compromise, malware deployment, or lateral movement. The lack of restrictions on command arguments and the unrestricted execution capability make this critical severity.

From the tool's definition Tool name 'run_cmd_tool' and description 'Execute CMD command with reliable output capture' explicitly state execution of arbitrary command-line commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_cmd_tool Rate-limited

run_cmd_tool 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": {
    "run_cmd_tool": {
      "limits": [
        {
          "counter": "run_cmd_tool_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 Windows Operations MCP, so you can run agents against it safely.

FAQ

Questions about run_cmd_tool

What does the run_cmd_tool tool do? +

Execute CMD command with reliable output capture. It is categorised as a Execute tool in the Windows Operations MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_cmd_tool? +

Register the Windows Operations MCP server in PolicyLayer and add a rule for run_cmd_tool: 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 Windows Operations MCP. Nothing to install.

What risk level is run_cmd_tool? +

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

Can I rate-limit run_cmd_tool? +

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

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

run_cmd_tool is provided by the Windows Operations MCP server (sandraschi/windows-operations-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.