shell_run_background · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What shell_run_background does on LocalAnt

AI agents invoke shell_run_background 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 shell_run_background needs a policy

This tool runs shell commands whose side effects depend entirely on what command is passed to it. While not inherently destructive (the agent could run harmless commands), the blast radius is high because background shell execution can modify system state, access credentials, install malware, exfiltrate data, or launch attacks.

From the tool's definition "Start a long-running command as a tracked background process" — this directly executes arbitrary shell commands in the background, with persistent effects determined by the command argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_run_background Rate-limited

shell_run_background 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": {
    "shell_run_background": {
      "limits": [
        {
          "counter": "shell_run_background_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 shell_run_background

What does the shell_run_background tool do? +

Start a long-running command as a tracked background process. Returns a processId. 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 shell_run_background? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for shell_run_background: 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 shell_run_background? +

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

Can I rate-limit shell_run_background? +

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

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

shell_run_background 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.