send_custom_command · Zont MCP: Risk & Policy

WHAT IT DOES

What send_custom_command does on Zont

AI agents invoke send_custom_command to trigger actions in Zont. 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 send_custom_command needs a policy

The name 'send_custom_command' strongly suggests this tool sends arbitrary or user-defined commands to the heating system, which falls under Execute. Given the context of a heating control system, misuse could affect physical infrastructure (boilers, heating circuits). However, the description is empty, which significantly lowers confidence.

From the tool's definition Tool name 'send_custom_command' implies execution of arbitrary commands against the ZONT heating system REST API.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_custom_command Rate-limited

send_custom_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": {
    "send_custom_command": {
      "limits": [
        {
          "counter": "send_custom_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 Zont, so you can run agents against it safely.

FAQ

Questions about send_custom_command

What does the send_custom_command tool do? +

send_custom_command. It is categorised as a Execute tool in the Zont MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_custom_command? +

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

What risk level is send_custom_command? +

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

Can I rate-limit send_custom_command? +

Yes. Add a rate_limit block to the send_custom_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 send_custom_command completely? +

Set action: deny in the PolicyLayer policy for send_custom_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 send_custom_command? +

send_custom_command is provided by the Zont MCP server (mab2908/zont-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.