mcp-video-analyzer

media MCP Server

MCP server for video analysis — extracts transcripts, key frames, OCR text, and metadata from video URLs. Supports Loom and direct video files.

Install Ready
mediamedia
8 views11 stars5 forksv0.2.5MIT

Why This Matters

Discovered via unknown and last synced 3mo ago.

Install Ready
Source
unknown
Stars
11
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

npx mcp-video-analyzer@latest

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-video-analyzer": {
      "command": "npx",
      "args": [
        "mcp-video-analyzer"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

14
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (14)

Key frames

extracted via scene-change detection (automatically deduplicated)

maxFrames

(1-60, default depends on detail level) — cap on extracted frames

OCR text

extracted from frames (code, error messages, UI text visible on screen)

threshold

(0.0-1.0, default 0.1) — scene-change sensitivity

Chapters

and **AI summary** (when available)

call

this tool when it sees a video URL — no need to ask.

Transcript

with timestamps and speakers

fields

— array of specific fields to return, e.g. `["metadata", "transcript"]`. Available: `metadata`, `transcript`, `frames`, `comments`, `chapters`, `ocrResults`, `timeline`, `aiSummary`

Comments

from viewers

Metadata

(title, duration, platform)

Annotated timeline

merging transcript + frames + OCR into a unified "what happened when" view

forceRefresh

— bypass cache and re-analyze

detail

— analysis depth: `"brief"` (metadata + truncated transcript, no frames), `"standard"` (default), `"detailed"` (dense sampling, more frames)

skipFrames

— skip frame extraction for transcript-only analysis