cli_execute · Cli Orchestrator MCP: Risk & Policy

WHAT IT DOES

What cli_execute does on Cli Orchestrator

AI agents invoke cli_execute to trigger actions in Cli Orchestrator. 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 cli_execute needs a policy

This tool executes tasks on external CLI services, which constitutes running code or triggering external operations whose effects depend on the arguments passed. While the resilience features (retry, circuit breaker, fallback) are defensive, they do not change the fundamental nature of the capability.

From the tool's definition Tool name is 'cli_execute' and description states it will 'Execute a task on a CLI' with routing to external services (Claude, Gemini, or Codex).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cli_execute Rate-limited

cli_execute 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": {
    "cli_execute": {
      "limits": [
        {
          "counter": "cli_execute_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 Cli Orchestrator, so you can run agents against it safely.

FAQ

Questions about cli_execute

What does the cli_execute tool do? +

Execute a task on a CLI (Claude, Gemini, or Codex) inline with automatic retry, circuit breaker, and fallback. It is categorised as a Execute tool in the Cli Orchestrator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cli_execute? +

Register the Cli Orchestrator MCP server in PolicyLayer and add a rule for cli_execute: 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 Cli Orchestrator. Nothing to install.

What risk level is cli_execute? +

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

Can I rate-limit cli_execute? +

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

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

cli_execute is provided by the Cli Orchestrator MCP server (lleontor705/cli-orchestrator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.