notify_telegram · Homelab MCP: Risk & Policy

WHAT IT DOES

What notify_telegram does on Homelab

AI agents use notify_telegram to create or update resources in Homelab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Homelab environment.

WHY IT NEEDS A POLICY

Why notify_telegram needs a policy

Sending a Telegram message is a Write operation: it creates new data (the message) in an external service but is reversible (the message can be deleted) and has no destructive side effects. While the server provides full Proxmox control, this specific tool is isolated to outbound notifications. Severity is low because misuse results only in spam messages, not system compromise, data loss, or financial impact.

From the tool's definition Tool description states 'Send a message to Telegram via the homelab bot' — this creates/sends data (a message) to an external service without deleting, modifying existing data, or executing code. The primary purpose is notification/communication.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

notify_telegram Rate-limited

notify_telegram stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "notify_telegram": {
      "limits": [
        {
          "counter": "notify_telegram_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Homelab, so you can run agents against it safely.

FAQ

Questions about notify_telegram

What does the notify_telegram tool do? +

Send a message to Telegram via the homelab bot. Use to confirm destructive operations, report issues found via MCP, or send homelab alerts. It is categorised as a Write tool in the Homelab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on notify_telegram? +

Register the Homelab MCP server in PolicyLayer and add a rule for notify_telegram: 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 Homelab. Nothing to install.

What risk level is notify_telegram? +

notify_telegram is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit notify_telegram? +

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

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

notify_telegram is provided by the Homelab MCP server (nainounen/homelab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.