videoscan-mcp
by guguborbh
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_DIR | No | Cache directory path. | ~/.videoscan/cache |
| VISION_MODEL | No | Optional vision model override. Defaults: gpt-4o / claude-sonnet-4-20250514 / gemini-2.0-flash. | |
| CACHE_ENABLED | No | Enable caching. | true |
| GOOGLE_API_KEY | No | Google API key for vision (Gemini). | |
| OPENAI_API_KEY | No | OpenAI API key for vision and transcription. | |
| VISION_PROVIDER | No | Vision provider for frame analysis: openai, anthropic, or google. Defaults to openai. | openai |
| CACHE_FRAMES_TTL | No | Frames cache TTL in seconds. | 86400 |
| DOWNLOAD_TIMEOUT | No | Download timeout in seconds. | 300 |
| ANTHROPIC_API_KEY | No | Anthropic API key for vision. | |
| CACHE_MAX_SIZE_GB | No | Maximum cache size in GB. | 5 |
| CACHE_RESULTS_TTL | No | Results cache TTL in seconds. | 604800 |
| MAX_DOWNLOAD_SIZE | No | Maximum download size in bytes. | 2147483648 |
| CACHE_DOWNLOAD_TTL | No | Download cache TTL in seconds. | 3600 |
| MAX_VIDEO_DURATION | No | Maximum video duration in seconds (0 for unlimited). | 3600 |
| VISION_CONCURRENCY | No | Max parallel vision API calls. | 5 |
| MAX_ANALYZED_FRAMES | No | Maximum number of frames to analyze. | 100 |
| TRANSCRIPTION_MODEL | No | Transcription model. | whisper-1 |
| FRAME_ANALYSIS_TIMEOUT | No | Frame analysis timeout in seconds. | 30 |
| TRANSCRIPTION_PROVIDER | No | Transcription provider: openai only for now. | openai |
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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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