shell_run_allowed_command · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What shell_run_allowed_command does on LocalAnt

AI agents invoke shell_run_allowed_command 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_allowed_command needs a policy

Execute category applies to tools that run code or shell commands whose effects depend on the arguments provided. Even though this tool is restricted to an allowlist (a significant security control), it still executes commands with side effects that depend on which allowlisted command is invoked and its arguments.

From the tool's definition Tool name 'shell_run_allowed_command' and description state it 'Run[s] a command' — this directly executes shell commands, placing it in the Execute category.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_run_allowed_command Rate-limited

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

FAQ

Questions about shell_run_allowed_command

What does the shell_run_allowed_command tool do? +

Run a command from the allowlist. Pipelines/redirection/chaining are rejected. 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_allowed_command? +

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

What risk level is shell_run_allowed_command? +

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

Can I rate-limit shell_run_allowed_command? +

Yes. Add a rate_limit block to the shell_run_allowed_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 shell_run_allowed_command completely? +

Set action: deny in the PolicyLayer policy for shell_run_allowed_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 shell_run_allowed_command? +

shell_run_allowed_command 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.