start_async_command · Run Command MCP Server MCP

WHAT IT DOES

What start_async_command does on Run Command MCP Server

AI agents invoke start_async_command to trigger actions in Run Command MCP Server. 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 start_async_command needs a policy

This tool falls squarely into the Execute category because it triggers external shell operations with unpredictable side effects based on user-supplied arguments. The severity is critical because unrestricted shell command execution poses the highest risk—a compromised AI agent could execute destructive, financial, or reconnaissance operations without user awareness.

From the tool's definition The tool description explicitly states it starts a command asynchronously and enables execution of shell commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_async_command Rate-limited

start_async_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_async_command": {
      "limits": [
        {
          "counter": "start_async_command_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 Run Command MCP Server, so you can run agents against it safely.

FAQ

Questions about start_async_command

What does the start_async_command tool do? +

Start a command asynchronously (non-blocking). Returns a process_id to check status and output later using get_command_output. It is categorised as a Execute tool in the Run Command MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_async_command? +

Register the Run Command MCP Server MCP server in PolicyLayer and add a rule for start_async_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 Run Command MCP Server. Nothing to install.

What risk level is start_async_command? +

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

Can I rate-limit start_async_command? +

Yes. Add a rate_limit block to the start_async_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 start_async_command completely? +

Set action: deny in the PolicyLayer policy for start_async_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 start_async_command? +

start_async_command is provided by the Run Command MCP Server MCP server (stilllovee/run-command-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.