Claude Telegram Supercharged
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API key used for Whisper transcription of voice messages (recommended, async and non-blocking). Set in ~/.claude/channels/telegram/.env. | |
| TELEGRAPH_ENABLED | No | Enable Telegraph (telegra.ph) Instant View publishing for long-form content (3000+ chars). Disabled by default because posts are publicly accessible by URL. Set to true to enable. | false |
| TELEGRAM_BOT_TOKEN | Yes | Your Telegram bot token from BotFather, e.g. 123456789:AAHfiqksKZ8... Set with /telegram:configure, written to ~/.claude/channels/telegram/.env, or exported in your shell (shell takes precedence). | |
| OPENAI_WHISPER_MODEL | No | Whisper model to use for transcription, e.g. gpt-4o-transcribe. Defaults to whisper-1 ($0.006/min). | |
| TELEGRAM_ROUTER_MODEL | No | Model used for routing requests: Haiku (fast, 200K), Sonnet (balanced, 1M), or Opus (deep, 1M). Complex tasks auto-escalate to Opus via subagents. | |
| TELEGRAM_ESCALATION_MODEL | No | Target model used when complex tasks auto-escalate via subagents. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues