Ask the user a question via Telegram and wait for their response
AI agents call ask_user to retrieve information from MCP-Communicator-Telegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool sends a question to a user via Telegram and retrieves their response. The primary action is querying the user for input and reading back their answer. While it does send a message (a minor write side-effect), the dominant purpose is to collect/read user input, making Read the most appropriate category.
From the tool's definition Ask the user a question via Telegram and wait for their response
Documented attack patterns abuse exactly the kind of access ask_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Communicator-Telegram, and nothing reaches the server without passing your rules. This is the rule we recommend for ask_user:
{
"version": "1",
"default": "deny",
"tools": {
"ask_user": {}
}
}ask_user 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.
Ask the user a question via Telegram and wait for their response. It is categorised as a Read tool in the MCP-Communicator-Telegram MCP Server, which means it retrieves data without modifying state.
Register the MCP-Communicator-Telegram MCP server in PolicyLayer and add a rule for ask_user: 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-Communicator-Telegram. Nothing to install.
ask_user 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 ask_user 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 ask_user. 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.
ask_user is provided by the MCP-Communicator-Telegram MCP server (qpd-v/mcp-communicator-telegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 MCP-Communicator-Telegram tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 MCP-Communicator-Telegram tools catalogued and risk-classified — across an index of 42,500+ MCP servers.