Telegram for AI agents -- messages, chats, media, and contacts across both bot and full user-account modes.
- capability exposure inferred + 28
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 5m ago · see ecosystem CVEs →
- B · 30 → B · 25
- C · 37 → B · 30
- C · 44 → C · 37
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 5a630fe · analyzer v28 · 13h ago
skills & prompt files 4
danger signals8
- suspicious endpoint t.me n24q02m-better-telegram-mcp-5a630fe/src/better_telegram_mcp/backends/bot_backend.py :76
"https://t.me/BotFather" - suspicious endpoint t.me n24q02m-better-telegram-mcp-5a630fe/tests/integration/test_bot_live.py :130
await bot.join_chat("https://t.me/+abc") - suspicious endpoint t.me n24q02m-better-telegram-mcp-5a630fe/tests/test_backends/test_bot_backend.py :172
await bot.join_chat("https://t.me/+abc") - suspicious endpoint 169.254.169.254 (cloud metadata) n24q02m-better-telegram-mcp-5a630fe/tests/test_backends/test_security.py :62
validate_url("http://169.254.169.254/latest/meta-data/") - suspicious endpoint 93.184.216.34 n24q02m-better-telegram-mcp-5a630fe/tests/test_backends/test_security.py :107
validate_url("https://93.184.216.34/image.jpg") - suspicious endpoint t.me n24q02m-better-telegram-mcp-5a630fe/tests/test_backends/test_user_backend.py :565
result = await backend.join_chat("https://t.me/joinchat/abc123") - suspicious endpoint api.telegram.org n24q02m-better-telegram-mcp-5a630fe/tests/test_full_live.py :66
resp = await client.get(f"https://api.telegram.org/bot{BOT_TOKEN}/getMe") - suspicious endpoint api.telegram.org n24q02m-better-telegram-mcp-5a630fe/tests/test_relay_setup.py :23
text = f"error posting https://api.telegram.org/bot{_FAKE_TOKEN}/getMe"
[](https://mcpobservatory.com/servers/github:n24q02m/better-telegram-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of n24q02m.