Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PROVIDERYesProvider to use: ollama, openai, openrouter
BATCH_SIZENoFrames per API call (0 = auto, defaults to 1)
MAX_FRAMESNoMax frames to send (default 60, hard cap 200)
FRAME_WIDTHNoFrame width in pixels (default 512)
OLLAMA_HOSTNoOllama server URL (default: http://localhost:11434)
MAX_COST_USDNoAbort if spend exceeds this (default 1.00)
MIN_INTERVALNoMinimum seconds between frames (default 2)
OLLAMA_MODELNoOllama model name (e.g., qwen2.5vl:3b)
OPENAI_MODELNoModel ID as shown in server (required)
FALLBACK_MODELNoModel ID for fallback
OPENAI_API_KEYNoAPI key for OpenAI-compatible server (e.g., lm-studio or not-needed)
OPENAI_BASE_URLNoBase URL for OpenAI-compatible server (e.g., http://localhost:1234/v1)
REQUEST_TIMEOUTNoPer-request timeout (default 600)
SCENE_THRESHOLDNoScene-change sensitivity 0–1 (default 0.1)
FALLBACK_API_KEYNoAPI key for fallback provider
OPENROUTER_MODELNoModel slug for OpenRouter (e.g., google/gemini-2.5-flash)
FALLBACK_BASE_URLNoBase URL for fallback server
FALLBACK_PROVIDERNoProvider for fallback (ollama/openai/openrouter)
OPENROUTER_API_KEYNoOpenRouter API key

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/arizawan/vidlizer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server