run_server_command | PolicyLayer

WHAT IT DOES

What run_server_command does on MCP Server & Client Test Environment

AI agents invoke run_server_command to trigger actions in MCP Server & Client Test Environment. 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_server_command needs a policy

This tool executes arbitrary terminal commands in the workspace, which has broad potential for side effects depending on what commands an AI agent chooses to run. It could install software, modify files, exfiltrate data, or perform any other shell operation. This qualifies as Execute rather than Destructive because the actual destructive potential depends entirely on the command arguments provided by the user/agent.

From the tool's definition Tool name 'run_server_command' combined with description 'Run a terminal command in workspace' explicitly indicates execution of arbitrary shell commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_server_command Rate-limited

run_server_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_server_command": {
      "limits": [
        {
          "counter": "run_server_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 MCP Server & Client Test Environment, so you can run agents against it safely.

FAQ

Questions about run_server_command

What does the run_server_command tool do? +

Run a terminal command in workspace. It is categorised as a Execute tool in the MCP Server & Client Test Environment 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_server_command? +

Register the MCP Server & Client Test Environment MCP server in PolicyLayer and add a rule for run_server_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 MCP Server & Client Test Environment. Nothing to install.

What risk level is run_server_command? +

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

Can I rate-limit run_server_command? +

Yes. Add a rate_limit block to the run_server_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_server_command completely? +

Set action: deny in the PolicyLayer policy for run_server_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_server_command? +

run_server_command is provided by the MCP Server & Client Test Environment MCP server (mayur11235/lets-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.