Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AGENT_NAMENoName the stdio adapter registers the session under (adapter `--name`). Default: claude.
AGENT_ROOMNoRoom the session joins (adapter `--room`). Default: default.
BRIDGE_HUBNoHub URL the stdio adapter connects to (adapter `--hub`). Default: ws://127.0.0.1:8765.
BRIDGE_HOSTNoHost the hub listens on. Keep it on localhost unless you also set a token. Default: 127.0.0.1.
BRIDGE_PORTNoPort the hub listens on. Default: 8765.
BRIDGE_PUSHNoPush mode for the stdio adapter (adapter `--push`). Default: channel; `wait` turns push off so messages are only returned by wait_for_message.
BRIDGE_TOKENNoToken that requires `Authorization: Bearer <token>` on every route (and `?token=` on WebSockets). No default; if unset, no auth is required.
BRIDGE_LOG_FILENoPath to a log file for the stdio adapter (adapter `--log-file`). Claude Code hides a stdio server's stderr, so use this to debug. No default.
AGENT_BRIDGE_WAKE_NAMENoOpencode wake plugin override for the agent name it polls for.
AGENT_BRIDGE_WAKE_SERVERNoOpencode wake plugin override for the MCP server entry it reads the hub URL, name and room from.
AGENT_BRIDGE_WAKE_DISABLENoSet to 1 to disable the Opencode wake plugin.
AGENT_BRIDGE_WAKE_INTERVALNoOpencode wake plugin polling interval in seconds. Default: 3.

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