Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODEX_BINNoPath to the `codex` executable. Auto-detected by default (searched in ~/.bun/bin, ~/.local/bin, ~/.npm-global/bin, ~/.cargo/bin, /usr/local/bin and /opt/homebrew/bin).
CODEX_HOMENoWhere the model cache and sessions are read from. This is the same variable Codex uses. Defaults to ~/.codex.
CODEX_DELEGATE_CWDNoBase directory for `cwd`. Defaults to the server's cwd.
CODEX_DELEGATE_AUTONoDefault for `auto`. Defaults to `true`.
CODEX_DELEGATE_FASTNo`true` or `false`: the default for `fast`. When unset, taken from config.toml.
CODEX_DELEGATE_EFFORTNoDefault reasoning effort. When unset, taken from config.toml.
CODEX_DELEGATE_SANDBOXNoDefault sandbox. Defaults to `workspace-write`.
CODEX_DELEGATE_TIMEOUTNoSeconds before a run is killed. Defaults to 1800.
CODEX_DELEGATE_MAX_OUTPUTNoMaximum number of response characters returned to Claude. Defaults to 40000.
CODEX_DELEGATE_READ_MODELNoModel used when `model` is omitted and the run is read-only. Defaults to the default model.
CODEX_DELEGATE_DEFAULT_MODELNoModel used when `model` is omitted. When unset, the model in your config.toml is used.

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