Telegram MCP
by NabuxAi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_DIR | No | Data directory (default: ./data) | |
| TG_API_ID | Yes | Telegram API ID from my.telegram.org (one pair for the whole server) | |
| TG_API_HASH | Yes | Telegram API hash from my.telegram.org (one pair for the whole server) | |
| LLM_PROVIDER | Yes | LLM/embedding provider: gemini, openai, or ollama | |
| ALLOWED_PHONES | No | Optional comma-separated list of allowed phone numbers | |
| APP_SECRET_KEY | Yes | Secret key used to encrypt Telegram sessions (Fernet) and sign cookies. Generate with: python3 -c "import secrets; print(secrets.token_urlsafe(48))" | |
| GEMINI_API_KEY | No | API key for Gemini (required if LLM_PROVIDER=gemini) | |
| OPENAI_API_KEY | No | API key for OpenAI (required if LLM_PROVIDER=openai) | |
| PUBLIC_BASE_URL | Yes | Public base URL of the server (e.g., https://mcp.example.com). For local testing, http://localhost:8000 is allowed. | |
| TELEGRAM_BOT_TOKEN | No | Optional Telegram bot token for the notebook bot (same archive) | |
| LOGIN_CODES_PER_HOUR | No | Optional rate limit for login codes per IP per hour |
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
ActivityMaintained
ResponsivenessNo issues