Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENCODE_BINNoPath to the `opencode` binary.auto-detected
OPENCODE_DELEGATE_CWDNoBase directory for `cwd`.project dir
OPENCODE_DELEGATE_AUTONoDefault for `auto`. Runs use `--auto` by default; set to false for read-only runs.true
OPENCODE_DELEGATE_TIMEOUTNoOptional hard cap in seconds, however busy the run is. `0` means none.0
OPENCODE_DELEGATE_MAX_OUTPUTNoMax response characters returned to Claude.40000
OPENCODE_DELEGATE_READ_MODELNoModel for read-only runs (`auto: false`) when none is given.the default model
OPENCODE_DELEGATE_IDLE_TIMEOUTNoA run that produces no output for this many seconds counts as stuck and is killed. `0` disables it.600
OPENCODE_DELEGATE_DEFAULT_MODELNoModel used when none is given.opencode's default
OPENCODE_DELEGATE_PREFERRED_PROVIDERSNoComma-separated provider order for models offered by several providers.

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