AI agents use tg_send_audio to create or update resources in Notify MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Notify MCP Server environment.
This tool sends audio files through Telegram, which creates new data (a message with audio content) in the Telegram platform. It is reversible (messages can be deleted by the user) and has no financial impact. The severity is medium because misuse could result in spam, harassment, or unwanted communications to Telegram users, but the blast radius is limited to message creation rather than system-level damage.
From the tool's definition Tool name 'tg_send_audio' and description 'Send audio via telegram bot' indicate creation of a new message/media object in a third-party service (Telegram).
Documented attack patterns abuse exactly the kind of access tg_send_audio gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Notify MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for tg_send_audio:
{
"version": "1",
"default": "deny",
"tools": {
"tg_send_audio": {
"limits": [
{
"counter": "tg_send_audio_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}tg_send_audio 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.
Send audio via telegram bot. It is categorised as a Write tool in the Notify MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Notify MCP Server MCP server in PolicyLayer and add a rule for tg_send_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 Notify MCP Server. Nothing to install.
tg_send_audio 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 tg_send_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 tg_send_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.
tg_send_audio is provided by the Notify MCP Server MCP server (oci:ghcr.io/aahl/mcp-notify:latest). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Notify MCP Server, 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.
21 Notify MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.