exec · Cargo MCP: Risk & Policy

WHAT IT DOES

What exec does on Cargo

AI agents invoke exec to trigger actions in Cargo. 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 needs a policy

This tool directly executes arbitrary commands in a containerized environment, which is the definition of Execute category. The explicit warning about untrusted code and the unconstrained nature of arbitrary command execution raises severity to critical—an AI agent given this tool with no guardrails could compromise the container, access sensitive data, modify the build environment, or pivot to other systems.

From the tool's definition Tool description explicitly states 'Executes arbitrary commands inside a running Docker container' and includes warning 'WARNING: may execute untrusted code.' The word 'arbitrary' indicates no restrictions on command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec Rate-limited

exec 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": {
      "limits": [
        {
          "counter": "exec_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 Cargo, so you can run agents against it safely.

FAQ

Questions about exec

What does the exec tool do? +

Executes arbitrary commands inside a running Docker container and returns structured output. WARNING: may execute untrusted code. It is categorised as a Execute tool in the Cargo 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? +

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

What risk level is exec? +

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

Can I rate-limit exec? +

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

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

exec is provided by the Cargo MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.