Get unread @mentions addressed to you in a Telegram chat. Marks all mentions as read on the server when all unread mentions fit within the requested limit.
AI agents call telegram-get-unread-mentions 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 tool retrieves unread mention data from Telegram chats. Although it performs a read operation on the server (marking mentions as read), this is a reversible state change typical of read operations (similar to marking emails as read). The tool does not create, modify content, execute code, delete data, or move money.
From the tool's definition Tool name contains 'get-unread' and description states 'Get unread @mentions' — a retrieval operation. While it has the side effect of marking mentions as read, the primary action is data retrieval with no irreversible consequences.
Documented attack patterns abuse exactly the kind of access telegram-get-unread-mentions 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-unread-mentions:
{
"version": "1",
"default": "deny",
"tools": {
"telegram-get-unread-mentions": {}
}
} telegram-get-unread-mentions 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.
Get unread @mentions addressed to you in a Telegram chat. Marks all mentions as read on the server when all unread mentions fit within the requested limit. 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-unread-mentions: 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-unread-mentions 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-unread-mentions 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-unread-mentions. 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-unread-mentions 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.