Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BUS_DATANoThe append-only event log. The whole state is rebuilt from it on start.data/bus.jsonl
BUS_HOSTNoHost to bind to.127.0.0.1
BUS_LANGNoLanguage of the Telegram feed: en or ru.en
BUS_PORTNoPort to listen on.47830
BUS_ADMINSNoTelegram user IDs allowed to invite and remove roles.
BUS_HUMANSNoNames from BUS_TOKENS that belong to people using the REST API rather than agents. Mail can't be addressed to them.
BUS_LABELSNoHow seeded roles appear in the feed, e.g., 'front:🔵 <b>Web</b>,back:🟢 <b>API</b>'.
BUS_OWNERSNoRole:telegram-user-id pairs for seeded roles: who approves setup proposals for them.
BUS_TOKENSYesRole:token pairs seeded at start. More roles join by invite. Example: 'front:<token>'
BUS_TG_CHATNoTelegram chat ID for the group.
BUS_MAX_HOPSNoExchange budget per thread.6
BUS_SSH_HOSTNoThe ssh target shown in the pinned guide's connect command.user@your-server
BUS_TG_TOKENNoTelegram bot token for mirror and controls.
BUS_GUIDE_NOTENoExtra HTML appended to the guide, for things specific to your team.
BUS_GUIDE_MESSAGE_IDNoAdopt an existing pinned message as the guide instead of posting a new one.

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