The MCP ecosystem often has several independent packages implementing the same tool — and "Telegram" currently has 14. Every one of them was scanned with the same deterministic engine, so the numbers below are directly comparable: the Trust Score (A–F), the capability blast radius, and how much of the package the scan could actually inspect. They are ranked by score; ties break toward unscoped, longer-established packages.
| Implementation | Package | Trust | Capability | Coverage | Findings | Scanned |
|---|---|---|---|---|---|---|
| Telegrambest by overpod | @overpod/mcp-telegram
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by beautyfree | mcp-telegram
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by cloud9-labs | @cloud9-labs/mcp-telegram
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by hlos-ai | mcp-server-telegram
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by kfastov | telegram-mcp-server
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by tonresistor | @tonresistor/telegram-mcp
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by zhigang1992 | @zhigang1992/telegram-mcp
npm |
A 100/100 | Minimal | Source | 0 | 2026-07-22 |
| Telegram by chaindead | @chaindead/telegram-mcp
npm |
A 98/100 | High | Source | 2 | 2026-07-22 |
| Telegram by iqai | @iqai/mcp-telegram
npm |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Telegram by itapi-core | @itapi-core/mcp-telegram
npm |
A 98/100 | Moderate | Source | 3 | 2026-07-22 |
| Telegram by dryeab | mcp-telegram
PyPI |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Telegram by PyPI | telegram-mcp
PyPI |
A 98/100 | Minimal | Source | 1 | 2026-07-22 |
| Telegram by npm | telegram-mcp
npm |
A 98/100 | High | Source | 2 | 2026-07-22 |
| Telegram by prgebish | @prgebish/mcp-telegram
npm |
B 87/100 | High | Source | 4 | 2026-07-22 |
A higher-ranked implementation is not "the official one" — ranking reflects only what the deterministic scan found in each published package. Open an implementation to read its individual findings with evidence, its scan history per version, and to grab an embeddable badge. Scores are automated opinions, recomputed on every rescan.