Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLog level for more verbose logging (e.g. INFO).
TG_MCP_LOGNoLog destination; set to /dev/null for tests.
TELEGRAM_API_IDYesTelegram API ID from my.telegram.org/apps. Required.
RADAR_NOTIFY_CMDNoShell command that receives market radar change text on stdin for delivery (Feishu, Slack, any notifier).
TRONGRID_API_KEYNoOptional key that raises the rate limit for on-chain USDT (Tron) lookups. Works without a key, rate-limited when busy.
RADAR_EVERY_HOURSNoInterval in hours for the market radar daemon to run on its own, timed from the last run recorded in the file so restarts don't reset it.24
TELEGRAM_API_HASHYesTelegram API hash from my.telegram.org/apps. Required.
TG_MCP_MEMORY_LIMIT_MBNoThe process exits on its own above this RSS in MB (default 2 GB); launchd restarts it.2048
TG_MCP_STARTUP_TIMEOUTNoSeconds before startup exits rather than hold the session while the first run pulls all dialogs to warm the cache.45
TELEGRAM_SESSION_STRINGNoSession string produced by running relogin.py and written to .env. If the same session string is used by two processes at once, Telegram revokes it.

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources