Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NAMESPACENoWhere runtimes and the server livesandbox-system
S3_BUCKETNoS3 backend: bucket name
S3_REGIONNoS3 backend: region
BASE_DOMAINNoApps are served at <name>.<sandbox_id>.<BASE_DOMAIN>sandbox.localhost
S3_ENDPOINTNoS3 backend: where the bucket is (endpoint)
S3_PROVIDERNoS3 backend: S3 provider
RUNTIME_CLASSNoPod runtime class; empty means the cluster defaultgvisor
SANDBOX_IMAGENoImage every runtime starts fromsandbox-base:latest
MAX_FILE_BYTESNowrite_file / read_file size cap in bytes5242880
STORAGE_BACKENDNoStorage backend: 'pvc' or 's3'pvc
S3_ACCESS_KEY_IDNoS3 backend: admin access key id, used only by this server
DEFAULT_CPU_LIMITNoPer-runtime CPU cap2
DEFAULT_TTL_MINUTESNoRuntime lifetime in minutes60
DEFAULT_MEMORY_LIMITNoPer-runtime memory cap4Gi
DEFAULT_STORAGE_SIZENoDefault storage size for the PVC backend10Gi
S3_SECRET_ACCESS_KEYNoS3 backend: admin secret access key, used only by this server
DEFAULT_STORAGE_CLASSNoDefault storage class for the PVC backendstandard
REAPER_INTERVAL_SECONDSNoHow often expired runtimes are swept60
S3_SYNC_INTERVAL_SECONDSNoHow often a runtime syncs its home5

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