command_run · Lockstep MCP: Risk & Policy

WHAT IT DOES

What command_run does on Lockstep

AI agents invoke command_run to trigger actions in Lockstep. 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 command_run needs a policy

Shell command execution is a quintessential Execute category action. It permits running arbitrary code on the host system with potentially severe side effects (reading/writing files, spawning processes, network calls, etc.). While not inherently destructive (if the command itself is benign), the blast radius is high if an AI agent misuses this tool with malicious or careless commands.

From the tool's definition Tool description states 'Run a shell command' — this directly executes arbitrary shell commands, which can trigger external operations, access the filesystem, and cause effects dependent on the command arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

command_run Rate-limited

command_run 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": {
    "command_run": {
      "limits": [
        {
          "counter": "command_run_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 Lockstep, so you can run agents against it safely.

FAQ

Questions about command_run

What does the command_run tool do? +

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

How do I enforce a policy on command_run? +

Register the Lockstep MCP server in PolicyLayer and add a rule for command_run: 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 Lockstep. Nothing to install.

What risk level is command_run? +

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

Can I rate-limit command_run? +

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

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

command_run is provided by the Lockstep MCP server (tmmoore286/lockstep-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.