shell_request_command_approval · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What shell_request_command_approval does on LocalAnt

AI agents invoke shell_request_command_approval 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_request_command_approval needs a policy

This tool enables execution of arbitrary shell commands on the host system (not pre-approved), which is a classic Execute category capability. The blast radius is high because shell commands can modify system state, access sensitive data, or trigger destructive operations depending on what the AI agent requests approval for.

From the tool's definition Tool name includes 'shell_request_command_approval' and description states it requests approval to run a command that is NOT on the allowlist.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_request_command_approval Rate-limited

shell_request_command_approval 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_request_command_approval": {
      "limits": [
        {
          "counter": "shell_request_command_approval_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_request_command_approval

What does the shell_request_command_approval tool do? +

Request approval to run a command that is NOT on the allowlist. Returns an approval id; once approved, call shell_run_approved_command. 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_request_command_approval? +

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

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

Can I rate-limit shell_request_command_approval? +

Yes. Add a rate_limit block to the shell_request_command_approval 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_request_command_approval completely? +

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

shell_request_command_approval 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.