shell_command · MCPServe MCP: Risk & Policy

WHAT IT DOES

What shell_command does on MCPServe

AI agents invoke shell_command to trigger actions in MCPServe. 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_command needs a policy

This tool directly executes arbitrary shell commands, giving an AI agent full system access to read files, modify system state, launch processes, and perform any operation the host system permits. The blast radius is critical because a compromised or misdirected prompt could result in data theft, system compromise, lateral movement, or destruction.

From the tool's definition Tool name: 'shell_command'. Description: 'Execute a shell command'. Shell command execution can run arbitrary code and trigger any system operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_command Rate-limited

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": {
    "shell_command": {
      "limits": [
        {
          "counter": "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 MCPServe, so you can run agents against it safely.

FAQ

Questions about shell_command

What does the shell_command tool do? +

Execute a shell command. It is categorised as a Execute tool in the MCPServe 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_command? +

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

What risk level is shell_command? +

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

Can I rate-limit shell_command? +

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

Set action: deny in the PolicyLayer policy for 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 shell_command? +

shell_command is provided by the MCPServe MCP server (mifunedev/mcp-sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.