telegram_send_voice · Agent Telegram MCP: Risk & Policy

WHAT IT DOES

What telegram_send_voice does on Agent Telegram

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

WHY IT NEEDS A POLICY

Why telegram_send_voice needs a policy

This tool creates new data (voice messages) on Telegram, which is reversible (messages can be deleted). It does not execute code, delete data, or move money. It is a Write operation because it creates/posts content. Severity is medium because misuse could result in spam or harassment via automated voice messages, but the impact is limited compared to destructive or financial actions.

From the tool's definition Tool name 'telegram_send_voice' indicates sending audio/voice messages via Telegram. Server description states the tool 'Enables AI agents to send and receive messages, media, and files on Telegram.' Sibling tools include 'telegram_send_audio' which confirms…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

telegram_send_voice Rate-limited

telegram_send_voice 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": {
    "telegram_send_voice": {
      "limits": [
        {
          "counter": "telegram_send_voice_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 Agent Telegram, so you can run agents against it safely.

FAQ

Questions about telegram_send_voice

What does the telegram_send_voice tool do? +

telegram_send_voice. It is categorised as a Write tool in the Agent Telegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on telegram_send_voice? +

Register the Agent Telegram MCP server in PolicyLayer and add a rule for telegram_send_voice: 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 Agent Telegram. Nothing to install.

What risk level is telegram_send_voice? +

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

Can I rate-limit telegram_send_voice? +

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

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

telegram_send_voice is provided by the Agent Telegram MCP server (tharindumendis/agent_telegeam_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.