Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
QUORUM_LISTENNo`host:port` to listen on. Keep it on loopback.127.0.0.1:8765
QUORUM_VEXA_URLNoVexa gateway base URL. Unset: Meet, Teams and Zoom answer `platform_unavailable`.
QUORUM_LOG_LEVELNo`debug`, `info`, `warn` or `error`. Logs are JSON lines on stderr.info
QUORUM_TOKEN_FILEYesFile holding the bearer token for `/mcp` and `/events`.
QUORUM_VEXA_VOICENoDefault for `meeting.join` `voice`: start Vexa bots able to speak.false
QUORUM_ECHO_WINDOW_SNoHow long the bot's own chat lines are recognised and dropped when Vexa reads them back.120
QUORUM_SAY_MAX_CHARSNoLongest `say` text (Vexa's own limit).1000
QUORUM_CHAT_MAX_CHARSNoLongest `chat.post` text.2000
QUORUM_MAX_BODY_BYTESNoLargest `/mcp` request body.1048576
QUORUM_TRANSCRIBE_URLNoBase URL of the Whisper service for Discord audio (`/v1/audio/transcriptions` is appended). Required for Discord.
QUORUM_LOBBY_TIMEOUT_SNoHow long a bot waits in a lobby before the meeting fails with `lobby_timeout`.600
QUORUM_SSE_HEARTBEAT_SNoInterval of `: ping` comments on `/events`.15
QUORUM_VEXA_TIMEOUT_MSNoTimeout for each Vexa REST call.15000
QUORUM_DISCORD_COMMANDSNoRegister `/hive` per guild (instant), `global`, or `off`.guild
QUORUM_TRANSCRIPT_BUFFERNoFinal segments kept per meeting for `transcript.read` and SSE replay.2000
QUORUM_VEXA_API_KEY_FILENoFile holding the tenant Vexa API key (scopes `bot`, `tx`), sent as `X-API-Key`.
QUORUM_DISCORD_SILENCE_MSNoSilence that ends a Discord utterance.800
QUORUM_DISCORD_TOKEN_FILENoFile holding the Discord bot token. Unset: Discord answers `platform_unavailable`.
QUORUM_MEETING_RETENTION_SNoHow long an ended meeting stays readable before quorum forgets it.3600
QUORUM_TRANSCRIBE_LANGUAGENoForce a transcription language (`en`, `de`, ...); unset lets Whisper detect it.
QUORUM_DISCORD_MAX_SEGMENT_SNoLonger speech is cut into segments of this length.30
QUORUM_DISCORD_REQUEST_TTL_SNoHow long a `/hive join` request waits for hive's approval.300
QUORUM_TRANSCRIBE_TIMEOUT_MSNoTimeout for each transcription request.60000
QUORUM_TRANSCRIBE_TOKEN_FILENoFile holding that service's API token, sent as `X-API-Key`.
QUORUM_DISCORD_JOIN_TIMEOUT_SNoHow long joining a voice channel may take.20
QUORUM_DISCORD_MIN_SEGMENT_MSNoUtterances shorter than this are dropped.300
QUORUM_VEXA_WS_BACKOFF_MAX_MSNoReconnect delay cap (exponential, jittered).30000
QUORUM_VEXA_WS_BACKOFF_MIN_MSNoFirst reconnect delay for the Vexa `/ws` feed.1000

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