Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DS_MODELNoModel used by every tool. Only change it when OpenCode Go ships a newer Flash.deepseek-v4.1-flash
DS_MAX_MODENoshell = ds_run may run commands; edit = edit only; read = only ds_explore/ds_ask. Anything else is treated as read.shell
DS_MAX_STEPSNoMax agent steps per job (callers can ask for fewer, not more).60
DS_STATE_DIRNoWhere job records and worktrees are kept.~/.opencode-deepseek
DS_TOKEN_BUDGETNoTokens (in + out) one job may spend before it is told to wrap up and report.2000000
OPENCODE_GO_KEYNoAlternative OpenCode Go API key variable accepted in place of OPENCODE_API_KEY.
DS_DENY_COMMANDSNoExtra regexes to block, separated by ;; (e.g. docker;;kubectl).
OPENCODE_API_KEYNoOpenCode Go API key (oc_sk_…). The server uses the first key found among plugin settings, OPENCODE_API_KEY, and OPENCODE_GO_KEY.
OPENCODE_BASE_URLNoOpenAI-compatible endpoint.https://opencode.ai/inference/go/openai/v1
DS_TASK_TIMEOUT_SECNoWall-clock limit per job in seconds (callers can ask for less, not more).1800
DS_SHELL_TIMEOUT_SECNoDefault per-command timeout in seconds.120
DS_ALLOW_ALL_COMMANDSNoSet to 1 to turn off the built-in deny-list (DS_DENY_COMMANDS still applies).

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