Turn short videos into timestamped text for LLMs: speech, on-screen text, and visual context.
Maintain this server? Claim it
This server only runs locally, from a package. Install it with the instructions on this page to try it.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add video-to-context \ -- uvx video-to-context==0.5.3
Environment
ANTHROPIC_API_KEY (optional, not in the config above): Optional Claude API key for visual analysis.VISION_BASE_URL (optional, not in the config above): Optional OpenAI-compatible vision endpoint, such as Ollama or Gemini.VISION_API_KEY (optional, not in the config above): Optional API key for the OpenAI-compatible endpoint.VISION_MODEL (optional, not in the config above): Vision model name. Required with VISION_BASE_URL.VIDEO_TEXT_ALLOWED_DIRS (optional, not in the config above): Optional folders the server may read local videos from.We don't run packages, so we can't list this server's tools.