auth_submit_code · Claudegram MCP: Risk & Policy

WHAT IT DOES

What auth_submit_code does on Claudegram

AI agents invoke auth_submit_code to trigger actions in Claudegram. 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 auth_submit_code needs a policy

This tool submits an authentication code (and optionally a 2FA password) to log into a personal Telegram account. Completing account authentication grants full access to all 120+ tools on this server, including messaging, media, chat management, and more. Misuse could result in unauthorized account takeover or enable a cascade of destructive/privacy-violating actions across the entire Telegram account.

From the tool's definition 'auth_submit_code' - Step 2: submit code (and optional 2FA password). This completes authentication to a Telegram account via MTProto.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

auth_submit_code Rate-limited

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

FAQ

Questions about auth_submit_code

What does the auth_submit_code tool do? +

Шаг 2: отправить код (и опц. пароль 2FA). It is categorised as a Execute tool in the Claudegram MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on auth_submit_code? +

Register the Claudegram MCP server in PolicyLayer and add a rule for auth_submit_code: 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 auth_submit_code? +

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

Can I rate-limit auth_submit_code? +

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

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

auth_submit_code 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.