AI agents use send_voice to create or update resources in Telegram MCP Complete — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Telegram MCP Complete environment.
This tool sends a voice message to a Telegram chat/user. It creates new content and initiates communication, which is a Write operation. Severity is high because an AI agent could misuse it to send unsolicited voice messages to many users across multiple accounts, given this is a multi-account management server with 123+ tools.
From the tool's definition send_voice: 发送语音消息 (Send voice message)
Documented attack patterns abuse exactly the kind of access send_voice gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Telegram MCP Complete, and nothing reaches the server without passing your rules. This is the rule we recommend for send_voice:
{
"version": "1",
"default": "deny",
"tools": {
"send_voice": {
"limits": [
{
"counter": "send_voice_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
发送语音消息. It is categorised as a Write tool in the Telegram MCP Complete MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Telegram MCP Complete MCP server in PolicyLayer and add a rule for 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 Telegram MCP Complete. Nothing to install.
send_voice is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
send_voice is provided by the Telegram MCP Complete MCP server (you922/telegram-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Telegram MCP Complete, 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.
153 Telegram MCP Complete tools catalogued and risk-classified — across an index of 43,000+ MCP servers.