desktop_commander_run_tool · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What desktop_commander_run_tool does on LocalAnt

AI agents invoke desktop_commander_run_tool to trigger actions in LocalAnt. 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 desktop_commander_run_tool needs a policy

This tool executes Desktop Commander tools, which are external operations whose effects depend on which tool is invoked and what arguments are passed. The high severity reflects that Desktop Commander can interact with the desktop environment (shells, browsers, files), creating substantial blast radius if an AI agent misuses it.

From the tool's definition Tool name includes 'run_tool' and description states it 'Run[s] a Desktop Commander tool through the MCP bridge.' The term 'run' combined with server context showing shell commands, browser automation, and file management capabilities indicates execution of…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

desktop_commander_run_tool Rate-limited

desktop_commander_run_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": {
    "desktop_commander_run_tool": {
      "limits": [
        {
          "counter": "desktop_commander_run_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about desktop_commander_run_tool

What does the desktop_commander_run_tool tool do? +

${DEPRECATED} Run a Desktop Commander tool through the MCP bridge. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on desktop_commander_run_tool? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for desktop_commander_run_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 LocalAnt. Nothing to install.

What risk level is desktop_commander_run_tool? +

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

Can I rate-limit desktop_commander_run_tool? +

Yes. Add a rate_limit block to the desktop_commander_run_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 desktop_commander_run_tool completely? +

Set action: deny in the PolicyLayer policy for desktop_commander_run_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 desktop_commander_run_tool? +

desktop_commander_run_tool is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.