run_command_with_log

THE RISK

High Risk

Why run_command_with_log needs a policy

RCON (Remote Console) commands on Minecraft servers can trigger a wide range of effects—from benign queries (list players) to destructive operations (stop server, delete world). The tool executes server commands whose effects depend on the specific command argument provided by the AI agent. This makes it Execute rather than Destructive (which would require the tool to inherently perform deletion/overwriting).

From the tool's definition Tool name 'run_command' combined with server purpose of executing commands via RCON. The sibling tool 'run_command' on a Minecraft RCON server executes arbitrary commands on the server.

Documented attack patterns abuse exactly the kind of access run_command_with_log gives an agent:

POLICY

How to control run_command_with_log

PolicyLayer is an MCP gateway — it sits between your AI agents and Minecraft RCON MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_command_with_log:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_command_with_log": {
      "limits": [
        {
          "counter": "run_command_with_log_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_command_with_log 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.

Create a free account and register Minecraft RCON MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Minecraft RCON MCP Server tools

Execute run_command Execute an RCON command on the Minecraft server (without leading slash). Read check_plugin_status Check overall plugin health: RCON connectivity, recent errors in the Read query_database Execute a read-only SELECT query against the plugin's SQLite database. Read read_server_log Read the last N lines from the Minecraft server log file. Read read_test_log read_test_log

All 6 Minecraft RCON MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Minecraft RCON MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_command_with_log

What does the run_command_with_log tool do? +

run_command_with_log. It is categorised as a Execute tool in the Minecraft RCON 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_command_with_log? +

Register the Minecraft RCON MCP Server MCP server in PolicyLayer and add a rule for run_command_with_log: 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 Minecraft RCON MCP Server. Nothing to install.

What risk level is run_command_with_log? +

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

Can I rate-limit run_command_with_log? +

Yes. Add a rate_limit block to the run_command_with_log 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_command_with_log completely? +

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

run_command_with_log is provided by the Minecraft RCON MCP Server MCP server (minecraftcodefoundary/minecraft-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Minecraft RCON MCP Server tool call.

Start from Minecraft RCON MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →