Fetch new messages, deleted messages, and other updates since a previously-known {pts, qts, date} cursor (from telegram-get-state or a prior call). Returns compact newMessages[], deletedMessageIds[], otherUpdates[] (className only), and the new cursor state. isFinal=false means more updates are q...
AI agents call telegram-get-updates 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.
This is a Read operation — it retrieves historical and real-time message data and account state. However, severity is high (not low/medium) because the tool operates as a userbot with 'full access to your chats, contacts, and message history' per the server description. An AI agent with unsupervised access to this tool could exfiltrate sensitive communications, contact lists, and private conversations at scale.
From the tool's definition Tool fetches 'new messages, deleted messages, and other updates' from Telegram account. Returns 'newMessages[], deletedMessageIds[], otherUpdates[]' without modifying any data.
Documented attack patterns abuse exactly the kind of access telegram-get-updates 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-get-updates:
{
"version": "1",
"default": "deny",
"tools": {
"telegram-get-updates": {}
}
}telegram-get-updates 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.
Fetch new messages, deleted messages, and other updates since a previously-known {pts, qts, date} cursor (from telegram-get-state or a prior call). Returns compact newMessages[], deletedMessageIds[], otherUpdates[] (className only), and the new cursor state. isFinal=false means more updates are queued — call again with the returned state. If Telegram reports the gap is too long, a fallback hint is returned suggesting to resync via telegram-read-messages per chat. Cursor is stateless — the agent must persist {pts, qts, date} between calls. 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-get-updates: 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-get-updates 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-get-updates 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-get-updates. 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-get-updates 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.