Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VISION_MODELNoVision model name for the selected provider.
VISION_API_KEYNoAPI key for the selected OpenAI-compatible vision provider. Not needed for local Ollama.
VISION_BASE_URLNoOpenAI-compatible base URL for the vision model, such as Gemini, OpenAI, OpenRouter, or a local Ollama server.
VISION_TIMEOUT_SNoTimeout in seconds for vision model requests.
ANTHROPIC_API_KEYNoClaude API key used for visual analysis with Claude.
VISION_MAX_FRAMESNoMaximum number of frames sent to the vision model per video.
VIDEO_TEXT_ALLOWED_DIRSNoFolders allowed for local video files. Local files are off by default.
VISION_REASONING_EFFORTNoReasoning effort for the vision model. Set to none to turn off model thinking.

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