# video-mcp
> Local video MCP for metadata, captions or Whisper transcripts, selected frames, OCR, and a merged timeline; optional yt-dlp handles platform URLs.
Canonical: https://www.mcpfolio.com/servers/video-mcp-neelsatyavolu
Last updated: 2026-10-28
## Catalog record

- Publisher: neelsatyavolu (community)
- Categories: search

## Website

https://github.com/neelsatyavolu/videomcp

## Repository

https://github.com/neelsatyavolu/videomcp

## Transports

stdio

## Authentication

Local processing needs no API key. OPENAI_API_KEY is an optional cloud transcription fallback; yt-dlp cookies may be configured for restricted platform URLs.

## Tools

- **video_check_deps**: Check availability of FFmpeg, yt-dlp, and transcription backends.
- **video_info**: Probe video duration, resolution, codecs, and audio presence.
- **video_transcribe**: Get timed speech from captions or a configured Whisper backend.
- **video_get_frame**: Return one JPEG frame at a requested time.
- **video_get_frame_burst**: Return multiple frames across a short window.
- **video_extract_frames**: Select frames by scene changes, intervals, or both.
- **video_analyze**: Combine probe, transcript, key frames, OCR, and timeline.
- **video_ocr**: Read on-screen text from key frames or one image.
- **video_search_transcript**: Find transcript segments matching a query.

## Sources

- [maintainer_repository_readme](https://github.com/neelsatyavolu/videomcp)
- [maintainer_server_source](https://github.com/neelsatyavolu/videomcp/blob/main/src/server.ts)
- [project_repository_icon](https://raw.githubusercontent.com/neelsatyavolu/videomcp/main/site/favicon.svg)
- [maintainer_repository_documentation](https://github.com/neelsatyavolu/videomcp)

## Setup

Use the interactive setup panel on [the detail page](https://www.mcpfolio.com/servers/video-mcp-neelsatyavolu) to view instructions for each supported client.