Claude Telegram Supercharged
by canm20
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 (recommended transcription method). Set in `~/.claude/channels/telegram/.env`. | |
| TELEGRAPH_ENABLED | No | Enable publishing long-form content to Telegraph (telegra.ph) as Instant View articles. Disabled by default because posts are publicly accessible by URL. Set to `true` to enable. | false |
| TELEGRAM_BOT_TOKEN | Yes | The Telegram bot token from BotFather (looks like `123456789:AAHfiqksKZ8...`). Can be set via `/telegram:configure <token>`, written to `~/.claude/channels/telegram/.env` as `TELEGRAM_BOT_TOKEN=...`, or set in your shell environment (shell takes precedence). | |
| OPENAI_WHISPER_MODEL | No | OpenAI transcription model. Defaults to `whisper-1`; can be switched, e.g. `gpt-4o-transcribe`. | whisper-1 |
| TELEGRAM_ROUTER_MODEL | No | Two-tier model routing configuration: Haiku (fast, 200K), Sonnet (balanced, 1M), or Opus (deep, 1M). | |
| TELEGRAM_ESCALATION_MODEL | No | The target model for complex tasks that auto-escalate via subagents. Defaults to Opus. |
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
ResponsivenessResponsive