High-risk tools in MCP-Telegram
4 of the 181 tools in MCP-Telegram are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
telegram-report-storyExecuteReport a story via the multi-step option flow. First call with option:
-
telegram-toggle-anti-spamExecuteEnable or disable aggressive anti-spam filtering in a supergroup. Supergroup only (not broadcast channels); requires admin with ban_users permission
-
telegram-loginExecuteLogin to Telegram via QR code. Returns QR image. IMPORTANT: pass the entire result to user without modifications.
-
telegram-press-buttonExecutePress an inline keyboard callback button on a message. Identify the button by (row, column) from its replyMarkup, or pass raw callback_data as base64. URL, switch-inline, game a...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.