Log inSubmit server
Video Reader MCP logo

Video Reader MCP

Reads local video metadata and subtitles, searches timestamped cues, and provides frame rendering, cropping, and OCR.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Video Reader MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "video-reader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sylphx/anymd"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 4 tools correctly (1mo ago).

Overview

Video Reader MCP MCP server reads local video files into a timestamped timeline with container metadata, stream details, chapters, and embedded subtitle cues. Its MCP tools can search those subtitle cues and perform a named follow-up to render, crop, or OCR a frame at a known timestamp. Scene detection is available through the quality profile, while speech recognition and automatic transcript extraction are not provided. Use it when an agent needs evidence-linked answers from local video rather than cloud video analysis.

Use cases

  • Search embedded subtitles for a quoted line
  • Identify chapters related to a topic
  • Inspect a frame at a known timestamp
  • Run OCR on a selected video frame
  • Detect scene boundaries in a demo

Key features

  • Reads container and stream metadata
  • Returns chapters and embedded subtitle cues
  • Searches subtitle cues without speech recognition
  • Detects scenes with the quality profile
  • Renders, crops, or OCRs timestamped frames
  • Provides timestamp and source-hash evidence

Tools4

What Video Reader MCP lets your agent do. Expand a tool for its parameters.

Verified live~3.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

Not checked yetLast checked 1d ago

We have not completed a health check for this listing yet.

11/24 checks healthy over the last 91d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · @sylphx/anymd (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads21kPackage downloads in the last 30 days.
Last commit1mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed4Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Video Reader MCP works

What Video Reader MCP MCP server does

Video Reader MCP works with local video files and returns structured information that an agent can use to locate and cite material. A default read includes container metadata, stream information, chapters, and embedded subtitles. Results can include timestamp values, stream indexes, subtitle ranges, and a source hash so an answer can point back to the input evidence.

The server is designed for questions such as finding a quoted line, identifying the chapter where a change occurs, or locating a useful moment in a recording. It does not create a transcript from audio. Subtitle-based answers depend on subtitles being embedded in the video; missing subtitles are reported as a gap rather than inferred.

How it works

Video Reader MCP uses a fast default profile for initial inspection. This profile does not detect scenes, extract frames, or run speech recognition. The quality profile adds ffmpeg scene detection, but it still does not extract frames or transcribe speech.

A typical workflow starts with read_video, providing an absolute local path in the sources input. An agent can then call search_video to find matching embedded subtitle cues. Once a relevant timestamp is available, video_evidence can render or crop a frame, or apply OCR to that frame. Frame indexes are only available after this evidence step.

The server keeps scene detection, frame work, and OCR separate from the initial read. This produces a timeline first and lets an agent request visual evidence only when it has a useful timestamp. Video Reader MCP does not require a cloud video API or a frame-by-frame vision model.

Setup and configuration

Run the released command with:

Terminal
npx -y @sylphx/cue

Claude Code can register it as a stdio MCP server with:

Terminal
claude mcp add cue -- npx -y @sylphx/cue

The repository README states that this project was merged into anymd on September 25, 2026 and is archived. The documented command above identifies the released Cue package associated with this repository.

The input uses a sources array containing local absolute paths. Omitting profile selects fast; setting profile to quality enables scene detection. include_keyframes and include_transcript remain unsupported in the shipped server and return a warning with an empty array when enabled.

Tools and capabilities

  • read_video: Reads metadata, streams, chapters, and embedded subtitles; scene detection is optional.
  • search_video: Searches embedded subtitle cues only and does not perform speech recognition.
  • video_evidence: Renders, crops, or OCRs one frame at a supplied timestamp.

Video Reader MCP is useful for meeting recordings, demos, and other local videos where an agent needs timestamp-level references. It can report warnings and gaps, including unavailable ffprobe data or absent embedded subtitles, instead of filling in unsupported information.

Limitations and notes

The server does not run speech recognition, generate a transcript, or automatically extract frames during the default read. Quality mode adds scene boundaries but not visual frame extraction. Subtitle search works only when the source contains embedded subtitles. OCR is limited to the frame requested through video_evidence.

The project is licensed under MIT.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Video Reader MCP

Video Reader MCP is an MCP server that connects AI agents to local video files through read_video, search_video, and video_evidence. It reads metadata, chapters, streams, and embedded subtitles; searches subtitle cues; and renders, crops, or OCRs a frame at a specified timestamp without performing speech recognition.

Run `npx -y @sylphx/cue` to start the released package. Claude Code can register it with `claude mcp add cue -- npx -y @sylphx/cue`. The repository is archived after being merged into anymd.

No, it searches embedded subtitle cues only. It does not run speech recognition or create a transcript, so a video needs embedded subtitles for subtitle-based quote searches.

Call `video_evidence` with a known timestamp to render or crop one frame, or to run OCR on it. The default `read_video` call does not extract frames, and frame indexes appear only after the evidence step.

Yes, scene detection is available when the `quality` profile is selected or scene inclusion is enabled. The feature uses ffmpeg scene detection and does not extract frames or perform speech recognition.

Related MCP servers

All in Multimedia Process All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewVideo Reader MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/video-reader-mcp?style=directory)](https://allmcps.com/mcp/video-reader-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/video-reader-mcp"><img src="https://allmcps.com/api/badge/video-reader-mcp?style=directory" alt="Video Reader MCP on AllMCPs" /></a>