shell · AgentExecMPC MCP: Risk & Policy

WHAT IT DOES

What shell does on AgentExecMPC

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

Shell command execution is a classic Execute action—it triggers arbitrary operations whose effects depend entirely on the arguments provided. The tool can run any shell command, making it extremely dangerous if an AI agent misuses it (e.g., deleting files, exfiltrating data, launching attacks). Severity is critical due to unrestricted blast radius in a multi-agent or untrusted-prompt scenario.

From the tool's definition Server description states it 'enables AI agents to safely execute shell commands' and tool is named 'shell'; tool description is empty but context from server documentation confirms shell command execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell Rate-limited

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

FAQ

Questions about shell

What does the shell tool do? +

shell. It is categorised as a Execute tool in the AgentExecMPC 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? +

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

What risk level is shell? +

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

Can I rate-limit shell? +

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

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

shell is provided by the AgentExecMPC MCP server (realugbun/agentexecmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.