Grade B
Telegram MCP by usefulapi
io.usefulapi/telegram · v1.8.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Read chats and members; send, edit and delete messages with a bot in Telegram.
Source: https://github.com/m190/usefulapi-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 9 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (telegram_delete_message). Require confirmation before the agent calls them. |
What was checked
- https://telegram.usefulapi.io/mcp: answers without auth
Public tools: telegram_get_me, telegram_get_chat, telegram_get_chat_member_count, telegram_get_chat_member, telegram_get_chat_administrators, telegram_get_updates, telegram_send_message, telegram_edit_message_text, telegram_delete_message
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-usefulapi-telegram-c8134616)