Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CACHE_DIRNoCache directory path.~/.videoscan/cache
VISION_MODELNoOptional vision model override. Defaults: gpt-4o / claude-sonnet-4-20250514 / gemini-2.0-flash.
CACHE_ENABLEDNoEnable caching.true
GOOGLE_API_KEYNoGoogle API key for vision (Gemini).
OPENAI_API_KEYNoOpenAI API key for vision and transcription.
VISION_PROVIDERNoVision provider for frame analysis: openai, anthropic, or google. Defaults to openai.openai
CACHE_FRAMES_TTLNoFrames cache TTL in seconds.86400
DOWNLOAD_TIMEOUTNoDownload timeout in seconds.300
ANTHROPIC_API_KEYNoAnthropic API key for vision.
CACHE_MAX_SIZE_GBNoMaximum cache size in GB.5
CACHE_RESULTS_TTLNoResults cache TTL in seconds.604800
MAX_DOWNLOAD_SIZENoMaximum download size in bytes.2147483648
CACHE_DOWNLOAD_TTLNoDownload cache TTL in seconds.3600
MAX_VIDEO_DURATIONNoMaximum video duration in seconds (0 for unlimited).3600
VISION_CONCURRENCYNoMax parallel vision API calls.5
MAX_ANALYZED_FRAMESNoMaximum number of frames to analyze.100
TRANSCRIPTION_MODELNoTranscription model.whisper-1
FRAME_ANALYSIS_TIMEOUTNoFrame analysis timeout in seconds.30
TRANSCRIPTION_PROVIDERNoTranscription provider: openai only for now.openai

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/guguborbh/videoscan-mcp'

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