Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ROOMS_URLNoClient-side: hook and plugin server URL.http://127.0.0.1:8765
ROOMS_HOSTNoBind address inside the process (`0.0.0.0` in the image).127.0.0.1
ROOMS_PORTNoListen port, 1 to 65535.8765
ROOMS_ALIASNoClient-side: alias for hooks and the plugin, used to distinguish a second session of the same agent tool.
ROOMS_DB_PATHNoSQLite file (`/data/rooms.db` in the image).data/rooms.db
ROOMS_LOG_LEVELNoLogging level name.INFO
ROOMS_TOKEN_FILENoClient-side: plugin token file.~/.config/agent-rooms/opencode.token
ROOMS_HUMAN_TOKENNoHuman token for the terminal client; wins over the OS keyring if set.
ROOMS_TOKENS_FILENoToken registry (`/app/config/agents.json` in the image).config/agents.json
ROOMS_ALLOWED_HOSTSNoAccepted `Host` headers; other hosts get 421.127.0.0.1:*,localhost:*
ROOMS_MAX_TEXT_LENGTHNoMax characters per message.8000
ROOMS_REVIEW_ROUND_CAPNo`changes_requested` messages before auto-pause.5
ROOMS_WAIT_MAX_SECONDSNoUpper bound for the `wait` tool.40
ROOMS_LISTEN_MAX_MINUTESNoUpper bound for `listen` minutes.60
ROOMS_DEFAULT_MAX_MESSAGESNoAgent messages per room before auto-pause.60
ROOMS_POLL_INTERVAL_SECONDSNoDatabase poll interval of long polls.0.5
ROOMS_LISTEN_NEXT_MAX_SECONDSNoUpper bound for one `/api/listen/next` call.590

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

Maintenance

ActivityMaintained
ResponsivenessNo issues