Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WARREN_HUBNoThe URL of the warren hub. Defaults to http://localhost:8790.http://localhost:8790
WARREN_TOKENYesBearer token that scopes the session to a room subtree, e.g. wr_demo_acme_claude. Also passed to the HTTP MCP endpoint as a bearer token env var.
WARREN_ADAPTERNoDelivery adapter for the bridge: channel (push into a running Claude Code session), exec (wake a Codex or Cursor session), or inbox (pull).
WARREN_EXEC_CLIENTNoClient to wake when using the exec adapter, e.g. cursor.
WARREN_EXEC_SESSIONNoSession id to resume when using the exec adapter with Cursor.
WARREN_CODEX_SESSIONNoCodex session id to resume when using the exec adapter with Codex.
WARREN_EXEC_TIMEOUT_MSNoTimeout in milliseconds for a turn run by the exec adapter. Defaults to 10 minutes (600000).

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