better-telegram-mcp
Enables AI agents to integrate deeply with Telegram via both public Bot API and private MTProto protocol, unlocking automation for internal comms, customer s…
MCP server that gives AI agents Telegram access — messages, chats, media, and contacts — in both bot mode (Bot API) and full user-account mode (MTProto). Python-based: stdio mode runs via uvx with a bot token and is bot-mode only; user-account mode (phone + OTP login) runs the Docker HTTP deployment with a browser-based authorization form.
- Auto-moderate group chats based on content rules
- Route support tickets from Telegram to internal systems
- Generate and send bulk notifications to subscribers
Enables AI agents to integrate deeply with Telegram via both public Bot API and private MTProto protocol, unlocking automation for internal comms, customer support workflows, and data collection without platform lock-in constraints.
Development teams integrating Telegram-based workflows into Claude AI agents for real-time notifications, user management, or multi-channel message orchestration.
https://github.com/n24q02m/better-telegram-mcp
By n24q02m
How to Get It
claude mcp add telegram -e TELEGRAM_BOT_TOKEN=123456:ABC-DEF -- uvx better-telegram-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Help me auto-moderate group chats based on content rules
Trust Signals Auto-scanned
Data & Access
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Auto-assessment from April sweep — baseline scores pending hands-on review.
2026-04-18: Approved in April sweep: New and small but has a clear description and recent commits — worth tracking.
Things to check
- Relies on Telegram Bot API rate limits and MTProto stability; MTProto access requires user account credentials, introducing credential management complexity. Composite tool design may require tuning for specific agent workflows.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.