Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OSI_KEYYesBearer key for authenticating to the OSI MCP endpoint. Generate with openssl rand -hex 32; give each client its own key.
API_PORTYesPort for the OSI REST and MCP endpoints.
ADMIN_KEYYesAdmin key used by OSI admin commands.
IMAGE_TAGYesDocker image tag; must match the built OSI image tag.
UPDATE_MODEYesUpdate mode for daytime embedding, for example debounce.
NIGHTLY_TIMEYesTime at which the nightly embedding/update run starts.
SCAN_SECONDSYesInterval in seconds at which the vault is scanned.
EMBED_GPU_URLNoURL of the GPU embedder entry. May be empty to use the CPU entry.
EMBED_MODEL_IDYesGGUF file name without the .gguf extension; checked against both router embedder entries.
DEBOUNCE_MINUTESNoDelay in minutes after a note's last change when UPDATE_MODE=debounce.
QUERY_LOG_RETENTION_DAYSYesNumber of days query logs are retained in /data before purging.
NIGHTLY_CPU_FALLBACK_MINUTESYesNumber of minutes at the end of the nightly window when the CPU entry takes over.

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