A
licenseNot graded
qualityB
maintenanceEnables AI agents to query local video timelines by extracting speech, frame captions, and on-screen text into a SQLite store, exposing search and retrieval tools via MCP.
PolyForm Noncommercial 1.0.0
video-reader-mcp
by SylphxAI
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., "@video-reader-mcpread video sample.mp4 including subtitles and scene changes"
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.
Cue
Video answers with timestamp-level proof
Cue gives agents a local video timeline they can search and cite: streams, chapters, subtitles, scenes, frames, and exact timestamps.
npx -y @sylphx/cueFor Claude Code:
claude mcp add cue -- npx -y @sylphx/cueThe fastest useful workflow
{
"sources": [{ "path": "/absolute/path/to/demo.mp4" }],
"include_subtitles": true
}Then ask:
“Find the moment where the presenter explains the pricing change.”
Cue returns the matching timestamp, surrounding transcript, source hash, and a route to render or crop the exact frame.
Related MCP server: Video MCP Server
Jobs Cue is built for
Ask your agent | Cue returns |
“Find this quote.” | timestamped transcript evidence |
“Summarize this meeting.” | chapters and subtitle-backed notes |
“Where is the code shown?” | timestamped frame and crop evidence |
“What changed in this demo?” | timeline and structural scene boundaries |
“Give me the useful moments.” | compact timeline with warnings and gaps |
Tool surface
Tool | Purpose |
| Build a local timeline from streams, subtitles, scenes, and keyframes |
| Search subtitles/transcripts and return timestamped matches |
| Render, crop, or OCR a frame at a known timestamp |
Predictable defaults
fastprobes streams and reads embedded metadata/subtitles.qualityexplicitly requests scene detection, keyframes, OCR, or local ASR.No cloud video API or frame-by-frame vision model is required.
Missing ffprobe, subtitles, or ASR is reported as a gap, not guessed around.
Why agents trust it
Every claim can point back to timestamp_ms, stream index, subtitle range,
frame index, or source hash. Structural keyframes are preferred over sampling
every frame.
Companion MCP tools
Product | Job |
PDF answers with page-level proof | |
Image facts and pixel evidence | |
Repository architecture and impact | |
Exact code-chunk retrieval | |
Web research with source excerpts |
Each product is independent. Install only the tools your agent needs.
Development
bun install
bun run build
bun test
cargo test
bun run benchmark:public-proof
bun run benchmark:release-gateLicense
MIT
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues
Related MCP Connectors
Fetch transcripts, subtitles, chapters, metadata and frames from YouTube and 10+ video platforms
Video analysis AI: transcripts, summaries, visual scenes/shots, clips, answers in natural language.
Extract structured insights from videos, podcasts, articles, and PDFs with multi-model AI
Any video URL to LLM-ready transcript. ASR built in, no captions needed. TikTok, X, TED and more.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceBridges Claude and video content by extracting keyframes and transcribing audio, enabling Claude to analyze video files.-
- AlicenseNot gradedqualityBmaintenanceEnables LLM agents to process local videos into timestamped, citable text documents and then query them through tools for listing videos, retrieving transcripts, and fetching specific segments, all fully offline.MIT
- AlicenseAqualityCmaintenanceEnables coding agents to turn videos from social platforms or local files into a small set of distinct frames plus a manifest, so they can answer visual questions by reading image paths. Also provides metadata lookup for captions and authors without downloading the video.2MIT