local-video-scenes-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@local-video-scenes-mcp extract scenes from screen-recording.mov"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Local Video Scenes MCP
Local Video Scenes MCP extracts timestamped screenshots from local videos so Claude can produce a visual walkthrough. It does not use Whisper, audio transcription, or any hosted video-processing service.
What Stays Local
The original video stays on your machine.
ffmpegandffproberun locally.The MCP returns local screenshot paths and metadata.
Claude analyzes only the screenshots you provide through the MCP result.
Audio is not extracted or analyzed in V1.
Related MCP server: Video MCP Server
Requirements
Node.js 18.18+
ffmpegandffprobe
The server includes video.check_ffmpeg, which reports whether ffmpeg/ffprobe are available and gives platform-specific install guidance. It also includes video.install_ffmpeg, which dry-runs by default and only runs package-manager commands when called with execute: true.
When a package manager is detected, it suggests commands such as:
brew install ffmpeg
winget install --id Gyan.FFmpeg -e
choco install ffmpeg -y
sudo apt-get install -y ffmpegMCP Configuration
After installing or building the package, configure your MCP client to run:
{
"mcpServers": {
"local-video-scenes": {
"command": "npx",
"args": ["local-video-scenes-mcp"]
}
}
}For local development from this repository:
{
"mcpServers": {
"local-video-scenes": {
"command": "node",
"args": ["/absolute/path/to/local-video-scenes-mcp/dist/server.js"]
}
}
}Tools
video.extract_scenes
Input:
{
"path": "/path/to/bug-demo.mp4",
"sensitivity": 0.3,
"minGapSeconds": 1.5,
"mode": "auto"
}Optional fields:
sensitivity: scene-change threshold between0and1; default0.3.maxFrames: maximum returned frames; defaultmin(80, max(12, ceil(durationSeconds / 3))).minGapSeconds: minimum gap between returned frames; default1.5.outputDir: output folder; default is a temp folder.mode:auto,scene, orsample; defaultauto.
Output includes:
durationsourcePathoutputDirextractionModemaxFramesperformanceEstimatewarningsframes[]withtimestamp,path,index, and optionalsceneScore
video.cleanup
Removes the generated frame directory:
{
"outputDir": "/tmp/video-context/abc123"
}video.check_ffmpeg
Checks local ffmpeg/ffprobe availability and returns install guidance if either is missing.
video.install_ffmpeg
Returns the detected install commands by default:
{
"execute": false
}To run the detected package-manager command, call it explicitly with:
{
"execute": true
}Performance Defaults
The default frame budget is tuned for 1-minute screen recordings:
maxFrames = min(80, max(12, ceil(durationSeconds / 3)))For a 60-second video, this returns about 20 frames by default. On an M2 with 16GB RAM, expected V1 behavior is:
ffmpeg extraction: usually 1-5 seconds
Claude visual walkthrough over 12-25 screenshots: roughly 10-30 seconds
target end-to-end time for a 1-minute video: under about 30 seconds in normal cases
Claude Usage Guidance
When a user provides a video path:
Call
video.extract_scenes.Inspect the returned image paths as visual context.
Produce a timestamped walkthrough of visible UI states, actions, errors, code, logs, and important text.
Mention that audio was not analyzed.
Use
video.cleanupwhen the generated screenshots are no longer needed.
Example:
The video shows the user opening the dashboard, navigating to Export, clicking the export action, and reaching a visible HTTP 500 error around 00:01:42. Audio was not analyzed.Development
npm install
npm test
npm run typecheck
npm run buildAvailable Tools
4 toolsvideo.check_ffmpegCheck ffmpegA
Check whether ffmpeg and ffprobe are available and return install guidance if not.
Inputs: no named parameters.
video.cleanupCleanup Video FramesB
Remove a generated video scene output directory.
Inputs: outputDir (required).
video.extract_scenesExtract Video ScenesA
Extract timestamped local screenshots from a video using ffmpeg scene detection with fallback sampling. Audio is not analyzed.
Inputs: path (required), mode, maxFrames, outputDir, +2 more.
video.install_ffmpegInstall ffmpegA
Return or run detected ffmpeg install commands. Dry-run by default; pass execute: true to run package-manager commands.
Inputs: execute.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: checking availability, installing, extracting scenes, and cleanup. No overlap in functionality.
All tools use a consistent 'video.' prefix and snake_case. The pattern verb_object (e.g., check_ffmpeg, extract_scenes) is maintained throughout.
Four tools adequately cover the essential workflow for a video scene extraction server: environment check, installation, extraction, and cleanup. The scope is well-balanced.
The tool surface covers the core operations (check, install, extract, cleanup). A minor gap is the lack of a read-only tool to list previously extracted scenes without re-running extraction, but overall it's sufficient.
Maintenance
Related MCP Connectors
Extract timestamped scene frames from video for AI vision, with OCR. Runs on Apify, pay per use.
Extract still frames from video URLs every N seconds, at scene changes or at named timestamps
Extract video frames from videos by just passing the url from youtube, tiktok, instagram or any other video url
Extract YouTube transcripts, search what was said, and read on-screen frames with cited timestamps.
Related MCP Servers
- -licenseAqualityNot gradedmaintenanceEnables extracting screenshots from video files at specific timestamps or intervals. Supports multiple video formats and output customization including resolution, quality, and format options.411 npm1-
- FlicenseNot gradedqualityDmaintenanceBridges Claude and video content by extracting keyframes and transcribing audio, enabling Claude to analyze video files.-
- AlicenseAqualityBmaintenanceEnables Claude Code, Codex, Claude Desktop and Cursor to see and hear MP4/MOV/MKV/WebM videos and screen recordings through timestamped keyframe storyboards, zoom and full-resolution frame drill-down, and a locally generated Whisper transcript. It also works with recording bundles that capture clicks and typed context, and runs entirely on the user's machine with no uploads or API keys.51MIT
- AlicenseNot gradedqualityBmaintenanceEnables an agent to process local video files and then read, search and inspect the results: timestamped transcripts, on-screen text and key frames as images. Everything runs locally, so an agent can answer questions like how to perform a task shown in a screencast or meeting recording.379 npm1MIT