run_cli_command · MCPHub MCP: Risk & Policy

WHAT IT DOES

What run_cli_command does on MCPHub

AI agents invoke run_cli_command to trigger actions in MCPHub. 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 run_cli_command needs a policy

CLI command execution is inherently Execute category—it triggers external operations (shell commands) whose effects depend entirely on the arguments provided. With an empty description offering no evidence of sandboxing, argument validation, or output filtering, an AI agent could trivially abuse this to read sensitive files, modify system state, exfiltrate data, or launch destructive actions (e.g., rm -rf /).

From the tool's definition Tool name 'run_cli_command' indicates execution of arbitrary command-line instructions. Empty description provides no constraints or safety guardrails.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_cli_command Rate-limited

run_cli_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": {
    "run_cli_command": {
      "limits": [
        {
          "counter": "run_cli_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 MCPHub, so you can run agents against it safely.

FAQ

Questions about run_cli_command

What does the run_cli_command tool do? +

run_cli_command. It is categorised as a Execute tool in the MCPHub MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_cli_command? +

Register the MCPHub MCP server in PolicyLayer and add a rule for run_cli_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 MCPHub. Nothing to install.

What risk level is run_cli_command? +

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

Can I rate-limit run_cli_command? +

Yes. Add a rate_limit block to the run_cli_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 run_cli_command completely? +

Set action: deny in the PolicyLayer policy for run_cli_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 run_cli_command? +

run_cli_command is provided by the MCPHub MCP server (jayden-dong/mcphub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.