Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENCODE_BASE_URLNoIf set, the bridge uses this existing opencode server instead of spawning one.
OPENCODE_BRIDGE_TOKENNoBearer token for MCP authentication. Strongly recommended before exposing through any tunnel; auto-generated by init if not set. Masked in output; printed only by show-token.
OPENCODE_SERVER_PASSWORDNoPassword for the managed opencode server. If not set, the bridge generates a random password per managed opencode server.
OPENCODE_BRIDGE_STALLED_MSNoThreshold in milliseconds after which a busy session is considered stalled. Default 120000, floor 5000.120000
OPENCODE_BRIDGE_CHECKPOINTSNoEnable or disable destructive tool checkpoints. Default true; set to false to disable.true
OPENCODE_BRIDGE_ALLOWED_ROOTSYesComma-separated list of allowed repository roots. Repositories must be under these roots; realpath-checked and re-validated on every call (deny by default).

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