shell.run · ForLoop MCP: Risk & Policy

WHAT IT DOES

What shell.run does on ForLoop MCP

AI agents invoke shell.run to trigger actions in ForLoop 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 shell.run needs a policy

Shell command execution is inherently Execute category: it runs code/commands whose effects depend entirely on the arguments provided. While the server applies governance and approval workflows as mitigations, these are operational controls, not capability limits.

From the tool's definition Tool explicitly "Run[s] a governed workspace command" - this triggers arbitrary shell execution in the workspace context. Description confirms execution capability with governance/approval workflows as controls rather than blockers.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell.run Rate-limited

shell.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": {
    "shell.run": {
      "limits": [
        {
          "counter": "shell.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 ForLoop MCP, so you can run agents against it safely.

FAQ

Questions about shell.run

What does the shell.run tool do? +

Run a governed workspace command only when this MCP server was started with shell enablement. It is categorised as a Execute tool in the ForLoop 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 shell.run? +

Register the ForLoop MCP server in PolicyLayer and add a rule for shell.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 ForLoop MCP. Nothing to install.

What risk level is shell.run? +

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

Can I rate-limit shell.run? +

Yes. Add a rate_limit block to the shell.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 shell.run completely? +

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

shell.run is provided by the ForLoop MCP server (master0ffate/forloop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.