Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GITHUB_TOKENNoGitHub token. Enables GitHub Models LLM rung.
GROQ_API_KEYNoGroq API key. Enables Groq speech-to-text and LLM rungs.
OLLAMA_MODELNoOllama model to use.
GEMINI_API_KEYNoGemini API key. Enables the Gemini AI Studio LLM rung.
LMSTUDIO_MODELNoLM Studio model to use.
OPENAI_API_KEYNoOpenAI API key. Enables paid OpenAI speech-to-text and LLM rungs.
LOCAL_LLM_MODELNoModel to use with the local OpenAI-compatible LLM server.
LOCAL_STT_MODELNoModel to use with the local OpenAI-compatible speech-to-text server.
MISTRAL_API_KEYNoMistral API key. Enables the Mistral LLM rung.
OLLAMA_BASE_URLNoOllama base URL.http://localhost:11434/v1
CEREBRAS_API_KEYNoCerebras API key. Enables Cerebras LLM rungs.
VID2CONTEXT_SKIPNoComma-separated names of services to skip, for example pollinations,ovh.
LMSTUDIO_BASE_URLNoLM Studio base URL.http://localhost:1234/v1
GROQ_FALLBACK_KEYSNoComma-separated extra Groq API keys. Each key becomes its own rung.
LOCAL_LLM_BASE_URLNoBase URL for any local OpenAI-compatible LLM server.
LOCAL_STT_BASE_URLNoBase URL for any local OpenAI-compatible speech-to-text server, such as speaches, faster-whisper-server, or LocalAI.
VID2CONTEXT_POLICYNoProvider selection policy: free (default: local, free, keyless, paid), local-only, or quality.free
VID2CONTEXT_KEYLESSNoSet to 0 to turn off keyless rungs, which send data to third parties without an account.
VID2CONTEXT_LOG_LEVELNoLog verbosity on stderr, for example info.
VID2CONTEXT_ALLOW_PAIDNoSet to 0 to never use paid rungs, even when a paid API key is set.

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