run_shell_command · Computer Use MCP Server MCP

WHAT IT DOES

What run_shell_command does on Computer Use MCP Server

AI agents invoke run_shell_command to trigger actions in Computer Use MCP Server. 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 run_shell_command needs a policy

This tool allows unrestricted execution of arbitrary shell commands on a macOS system. The blast radius is maximal: an AI agent could delete files, exfiltrate data, install malware, modify system configuration, escalate privileges, or compromise the entire machine. Shell command execution is the canonical Execute category risk.

From the tool's definition Tool name is 'run_shell_command' with description: 'Execute a shell command and return its output (stdout, stderr, return code).' The verb 'Execute' and explicit reference to shell command execution directly indicate this tool runs arbitrary code on the…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_shell_command Rate-limited

run_shell_command 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": {
    "run_shell_command": {
      "limits": [
        {
          "counter": "run_shell_command_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 Computer Use MCP Server, so you can run agents against it safely.

FAQ

Questions about run_shell_command

What does the run_shell_command tool do? +

Execute a shell command and return its output (stdout, stderr, return code). It is categorised as a Execute tool in the Computer Use MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_shell_command? +

Register the Computer Use MCP Server MCP server in PolicyLayer and add a rule for run_shell_command: 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 Computer Use MCP Server. Nothing to install.

What risk level is run_shell_command? +

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

Can I rate-limit run_shell_command? +

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

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

run_shell_command is provided by the Computer Use MCP Server MCP server (syedazharmbnr1/computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.