send_dice · Claudegram MCP: Risk & Policy

WHAT IT DOES

What send_dice does on Claudegram

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

WHY IT NEEDS A POLICY

Why send_dice needs a policy

The tool sends an interactive dice message to a Telegram chat. This is a Write operation as it creates a new message in a conversation. Misuse could involve sending unwanted messages to contacts, but it is reversible in the sense that messages can be deleted. Severity is medium due to potential for spam or harassment via automated messaging.

From the tool's definition Отправить интерактивный «кубик»

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_dice Rate-limited

send_dice 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": {
    "send_dice": {
      "limits": [
        {
          "counter": "send_dice_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 Claudegram, so you can run agents against it safely.

FAQ

Questions about send_dice

What does the send_dice tool do? +

Отправить интерактивный «кубик». It is categorised as a Write tool in the Claudegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_dice? +

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

What risk level is send_dice? +

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

Can I rate-limit send_dice? +

Yes. Add a rate_limit block to the send_dice 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_dice completely? +

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

send_dice is provided by the Claudegram MCP server (sanjar-x/claudegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.