AgentStack
MCP unreviewed MIT Self-run

45telega

mcp-sergekostenchuk-45telega · by sergekostenchuk

Telegram MCP server with 45+ methods, QR auth, WSL/Kiro setup, and Docker-ready deployment

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add mcp-sergekostenchuk-45telega

Open-source listing — not yet scanned by AgentStack. Follow the source repository for install instructions.

Security review

⚠ Flagged

1 finding(s); flagged for manual review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures
  • high Pipes remote content directly into a shell (remote code execution).

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets Used
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of 45telega? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

🚀 45telega - Production-Ready Telegram MCP Server

[](https://github.com/sergekostenchuk/45telega/releases) [](https://pypi.org/project/45telega/) [](LICENSE) [](setup.py)

A powerful Model Context Protocol (MCP) server for Telegram with 45+ methods, production-ready deployment, and enterprise features.

✨ Features

  • 45+ Telegram Methods: Complete API coverage for messages, chats, users, media
  • Production Ready: Docker support, health checks, monitoring, logging
  • Secure: Non-root container, environment-based config, session encryption
  • Scalable: Async architecture, Redis caching, connection pooling
  • Easy Install: One-line installation, auto-updates, multiple deployment options

🚀 Quick Start

Platform-Specific Setup

🪟 Windows + WSL + Kiro IDE

[📖 Complete Windows Setup Guide →](WINDOWSWSLSETUP.md)

Comprehensive step-by-step guide for Windows users with WSL and Kiro IDE integration.

🐧 Linux/macOS

One-Line Install

curl -sSL https://raw.githubusercontent.com/sergekostenchuk/45telega/main/install.sh | bash

PyPI Install

pip install 45telega

Docker Install

docker run -d \
  --name 45telega \
  -p 8765:8765 \
  -e TELEGRAM_API_ID=your_api_id \
  -e TELEGRAM_API_HASH=your_api_hash \
  -v $(pwd)/data:/data \
  ghcr.io/sergekostenchuk/45telega:latest

📋 Prerequisites

  • Python 3.9+ or Docker
  • Telegram API credentials from my.telegram.org
  • 512MB RAM minimum
  • Linux/macOS/Windows (with WSL)

🔧 Configuration

1. Get Telegram API Credentials

  1. Go to my.telegram.org
  2. Login with your phone number
  3. Create new application
  4. Copy api_id and api_hash

2. Configure Environment

Copy .env.example to .env:

cp ~/.config/45telega/.env.example ~/.config/45telega/.env

Edit with your credentials:

TELEGRAM_API_ID=your_api_id_here
TELEGRAM_API_HASH=your_api_hash_here
TELEGRAM_PHONE=+1234567890  # Optional

3. First Authentication

45telega sign-in --phone +1234567890

Enter the code you receive on Telegram.

🎯 Usage

Start MCP Server

# Native
45telega run

# Docker
docker-compose up -d

# With custom port
45telega run --port 9000

Add to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "45telega": {
      "type": "stdio",
      "command": "/Users/you/.local/bin/45telega",
      "args": ["run"],
      "env": {
        "TELEGRAM_API_ID": "your_api_id",
        "TELEGRAM_API_HASH": "your_api_hash"
      }
    }
  }
}

Add to Kiro IDE (Windows + WSL)

See the [Windows Setup Guide](WINDOWSWSLSETUP.md) for detailed Kiro IDE integration instructions.

📚 Available Methods

Messages

  • SendMessage - Send text messages
  • EditMessage - Edit existing messages
  • DeleteMessage - Delete messages
  • ForwardMessage - Forward messages
  • ReplyToMessage - Reply to specific messages
  • SendFile - Send files/media

Chats

  • GetChats - List all chats
  • GetChatInfo - Get chat details
  • GetChatMembers - List chat members
  • CreateGroup - Create new group
  • CreateChannel - Create new channel
  • JoinChatByInvite - Join via invite link

Users

  • GetMe - Get current user info
  • GetUserInfo - Get user details
  • GetContacts - List contacts
  • AddContact - Add new contact
  • BlockUser - Block user
  • UnblockUser - Unblock user

Full API Documentation →

🐳 Docker Deployment

docker-compose.yml

version: '3.8'
services:
  45telega:
    image: ghcr.io/sergekostenchuk/45telega:latest
    restart: unless-stopped
    ports:
      - "8765:8765"
    volumes:
      - ./data:/data
      - ./logs:/logs
    env_file:
      - .env

Run with Docker Compose

docker-compose up -d
docker-compose logs -f  # View logs
docker-compose down     # Stop

🔒 Security

  • Non-root container: Runs as unprivileged user
  • Environment variables: No hardcoded credentials
  • Session encryption: Secure session storage
  • Rate limiting: Built-in protection
  • Health checks: Automatic recovery

📊 Monitoring

Health Check

curl http://localhost:8765/health

Prometheus Metrics

Enable in .env:

PROMETHEUS_ENABLED=true
PROMETHEUS_PORT=9090

Logging

Logs are stored in ./logs/ with rotation:

tail -f logs/45telega.log

🔄 Updates

Auto-update

45telega update

Manual Update

cd ~/.local/share/45telega
git pull
pip install -e . --upgrade

🧪 Development

Setup Development Environment

git clone https://github.com/sergekostenchuk/45telega
cd 45telega
pip install -e .[dev]

Run Tests

pytest tests/
pytest --cov=telega45  # With coverage

Code Quality

black .          # Format code
ruff check .     # Lint
mypy telega45    # Type check

🤝 Contributing

  1. Fork the repository
  2. Create feature branch (git checkout -b feature/amazing)
  3. Commit changes (git commit -m 'Add amazing feature')
  4. Push to branch (git push origin feature/amazing)
  5. Open Pull Request

📝 License

MIT License - see [LICENSE](LICENSE) file.

💬 Support

🙏 Acknowledgments

  • Telethon - Telegram client library
  • MCP - Model Context Protocol
  • Claude - AI assistant platform

Made with ❤️ by Sergey Kostenchuk

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.