Request server-side transcription of a voice note or video note (Telegram Premium feature). Returns immediately with transcriptionId — if pending:true, call telegram-get-transcription to poll for completion.
AI agents call telegram-transcribe-audio to retrieve information from MCP-Telegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Transcription is fundamentally a read operation—it retrieves and processes existing voice/video data without modifying, deleting, or executing arbitrary code. However, severity is elevated to medium because: (1) it accesses private voice messages that the user may not have authorized the AI to transcribe, (2) it operates under a personal Telegram account (userbot) with full chat/contact access per server…
From the tool's definition The tool 'transcribes' audio by requesting Telegram's server-side transcription service and returns transcription data.
Documented attack patterns abuse exactly the kind of access telegram-transcribe-audio gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Telegram, and nothing reaches the server without passing your rules. This is the rule we recommend for telegram-transcribe-audio:
{
"version": "1",
"default": "deny",
"tools": {
"telegram-transcribe-audio": {}
}
} telegram-transcribe-audio is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Request server-side transcription of a voice note or video note (Telegram Premium feature). Returns immediately with transcriptionId — if pending:true, call telegram-get-transcription to poll for completion. It is categorised as a Read tool in the MCP-Telegram MCP Server, which means it retrieves data without modifying state.
Register the MCP-Telegram MCP server in PolicyLayer and add a rule for telegram-transcribe-audio: 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 MCP-Telegram. Nothing to install.
telegram-transcribe-audio is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the telegram-transcribe-audio 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.
Set action: deny in the PolicyLayer policy for telegram-transcribe-audio. 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.
telegram-transcribe-audio is provided by the MCP-Telegram MCP server (mcp-telegram/mcp-telegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-Telegram, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
181 MCP-Telegram tools catalogued and risk-classified — across an index of 43,000+ MCP servers.