Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNostderr logging verbosity.INFO
TTS_MODELNoAny TTS model on OpenRouter's /audio/speech endpoint.fish-audio/s1
TTS_VOICENoVoice name, if the model supports it.
TTS_BASE_URLNoAny OpenAI-compatible audio API works.https://openrouter.ai/api/v1
TELEGRAM_PROXYNosocks5://host:port or http://host:port for MTProto (Telethon ignores HTTP_PROXY).
TELEGRAM_API_IDYesAPI ID from my.telegram.org (required).
CALL_REPEAT_PAUSENoPause between repeats, seconds.2
TELEGRAM_API_HASHYesAPI hash from my.telegram.org (required).
MAX_MESSAGE_LENGTHNoMessage length cap after sanitization.500
OPENROUTER_API_KEYYesOpenRouter API key for TTS (required).
CALL_ANSWER_TIMEOUTNoSeconds to wait for the callee to answer.45
CALL_TARGET_USER_IDYesNumeric Telegram user ID to call (required).
TELEGRAM_SESSION_PATHNoSession file location (without .session).~/.telegram-call-mcp/telegram

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
make_callA

Place a real Telegram voice call to the owner and speak the message aloud.

Use this when something is urgent enough to interrupt the owner with a ringing phone call — a critical incident, a failed deployment, anything they asked to be actively alerted about. The call rings like a normal Telegram call; once answered, the synthesized message plays repeat times and the call hangs up. The whole attempt can take up to ~2 minutes (ring timeout + playback). The result reports whether the owner answered ("answered"), didn't pick up ("no_answer"), was on another call ("busy"), or declined ("declined") — an unanswered call means the message was NOT delivered, so consider retrying later or falling back to a text message.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/maloleg/telegram-call-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server