exec_run · Promethean OS MCP: Risk & Policy

WHAT IT DOES

What exec_run does on Promethean OS MCP

AI agents invoke exec_run to trigger actions in Promethean OS MCP. 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 exec_run needs a policy

This tool executes shell commands, which is the defining characteristic of the Execute category. Shell command execution can trigger external operations with side effects dependent on the command arguments. While the tool claims commands are 'vetted' and from an 'allowlist', this is a control mechanism rather than a category change—execution still occurs.

From the tool's definition Tool description states 'Execute a vetted shell command' which directly performs shell execution. The term 'Execute' combined with 'shell command' indicates code/command execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec_run Rate-limited

exec_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": {
    "exec_run": {
      "limits": [
        {
          "counter": "exec_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 Promethean OS MCP, so you can run agents against it safely.

FAQ

Questions about exec_run

What does the exec_run tool do? +

Execute a vetted shell command from the allowlist. Supports optional args when explicitly enabled. It is categorised as a Execute tool in the Promethean OS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on exec_run? +

Register the Promethean OS MCP server in PolicyLayer and add a rule for exec_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 Promethean OS MCP. Nothing to install.

What risk level is exec_run? +

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

Can I rate-limit exec_run? +

Yes. Add a rate_limit block to the exec_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 exec_run completely? +

Set action: deny in the PolicyLayer policy for exec_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 exec_run? +

exec_run is provided by the Promethean OS MCP server (octave-commons/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.