Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging level. Valid values are DEBUG, INFO, WARNING, or ERROR.INFO
MAX_STEPSNoNumber of specialist visits before a forced finish.8
MEMORY_DIRNoDirectory for the short-term scratchpad and long-term SQLite memory files..memory
LLM_PROVIDERNoModel provider to use. Valid values are 'stub' or 'openai'.stub
OPENAI_MODELNoChat model name used when LLM_PROVIDER is 'openai'.gpt-4o-mini
OPENAI_API_KEYNoRequired only for a live OpenAI call. If missing, the server falls back to the stub provider.
OPENAI_BASE_URLNoAPI root used when LLM_PROVIDER is 'openai'.https://api.openai.com/v1
SHORT_TERM_WINDOWNoNumber of messages kept per short-term memory thread.12

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

Maintenance

ActivityMaintained
ResponsivenessNo issues