Analyze the given video and answer the user's question (or summarize it if no question was asked). Always cite timestamps (M:SS) in your answer.
Route A — video-analyzer MCP tools available (preferred)
If the video-analyzer MCP server is connected in this session, call its tools directly — do not use the CLI:
- General question or no question →
analyze_video (detail "standard")
- "What happens at X:XX" / a specific moment →
analyze_moment (time range) or get_frame_at
- Question answerable from speech alone →
get_transcript (fast, no download)
- Title / duration / views / comments only →
get_metadata (no download)
- Motion or fast UI changes →
get_frame_burst
Dense UI capture (terminal, dashboard, IDE, spreadsheet — the meaning is in small text): pass maxWidth on any of these tools. Emitted frames are capped at 800 px wide by default, which turns a 1920×1080 screencast into 800×450 and drops a 15 px UI font below what a vision model can read. maxWidth: 0 keeps the source resolution; a value like 1568 is the middle ground. Native frames cost several times more context, so raise it for the close read, not for the overview.
Route B — no MCP server (any agent with a shell)
Run the one-shot CLI via Bash (first run downloads the npm package — slow is not broken; progress streams on stderr):
npx -y mcp-video-analyzer@latest analyze "<video-url-or-path>"
stdout is a single JSON document: metadata, transcript (timestamped entries), ocrResults (on-screen text), timeline, warnings, and frames — an array of { time, filePath, mimeType } pointing to JPEG key frames on disk. Then:
- Parse the JSON from stdout.
- Read the
frames[].filePath images (in parallel) when the question needs visuals.
- Answer from transcript + OCR + frames, citing timestamps.
Useful flags: --detail brief|standard|detailed (brief = metadata + transcript only, no frame extraction — the fast/cheap path), --fields metadata,transcript (filters the emitted JSON only; frames are still computed at standard detail), --max-frames <1-60>, --max-width <px> (frame width cap, default 800; 0 keeps source resolution — use it for dense UI captures whose payload is small text), --language <code> (force transcription language), --out <dir> (where frames are copied), --force-refresh. Run npx -y mcp-video-analyzer@latest analyze --help for the full list.
Prerequisites & degradation
- Node.js 22.12+ (required).
ffmpeg is bundled — no install needed.
- Platform URLs (YouTube, Instagram, TikTok, …) require
yt-dlp on PATH; direct .mp4/.webm/.mov URLs and local files work without it. Loom transcript, metadata, and comments need no yt-dlp either. Loom frames usually do — Loom serves most videos as separate DASH video+audio streams that only yt-dlp fetches and merges; a CDN fallback covers some videos without it.
- The tool never fails on partial results: the
warnings array carries actionable hints (yt-dlp install, YTDLP_COOKIES_FROM_BROWSER for Instagram/age-restricted, missing Whisper backend). Relay relevant warnings to the user instead of treating them as errors.
- An empty transcript alongside a "silent audio" warning means the video genuinely has no speech (common for muted Reels/Stories) — that is content, not a failure.
- Only
http(s) URLs to public addresses are accepted. A URL on localhost, a private/LAN range, a .local name, a UNC share, or a non-HTTP scheme is rejected up front with a message saying so — that is a deliberate refusal, not a transient error, so do not retry it or try to work around it. When the user really does want a video from their own network, tell them to restart the server with MCP_ALLOW_PRIVATE_URLS=1. Cloud metadata endpoints stay blocked even then.
1---2name: video3description: Analyze a video (Loom, YouTube, Vimeo, TikTok, Instagram, X/Twitter, Twitch, Dailymotion, Facebook, direct URL, or local file) — transcript, key frames, OCR text, metadata, annotated timeline — and answer questions about it with timestamps.4license: MIT5---67Analyze the given video and answer the user's question (or summarize it if no question was asked). Always cite timestamps (`M:SS`) in your answer.89## Route A — video-analyzer MCP tools available (preferred)1011If the `video-analyzer` MCP server is connected in this session, call its tools directly — do not use the CLI:1213- General question or no question → `analyze_video` (detail `"standard"`)14- "What happens at X:XX" / a specific moment → `analyze_moment` (time range) or `get_frame_at`15- Question answerable from speech alone → `get_transcript` (fast, no download)16- Title / duration / views / comments only → `get_metadata` (no download)17- Motion or fast UI changes → `get_frame_burst`1819**Dense UI capture** (terminal, dashboard, IDE, spreadsheet — the meaning is in small text): pass `maxWidth` on any of these tools. Emitted frames are capped at 800 px wide by default, which turns a 1920×1080 screencast into 800×450 and drops a 15 px UI font below what a vision model can read. `maxWidth: 0` keeps the source resolution; a value like `1568` is the middle ground. Native frames cost several times more context, so raise it for the close read, not for the overview.2021## Route B — no MCP server (any agent with a shell)2223Run the one-shot CLI via Bash (first run downloads the npm package — slow is not broken; progress streams on stderr):2425```bash26npx -y mcp-video-analyzer@latest analyze "<video-url-or-path>"27```2829stdout is a single JSON document: `metadata`, `transcript` (timestamped entries), `ocrResults` (on-screen text), `timeline`, `warnings`, and `frames` — an array of `{ time, filePath, mimeType }` pointing to JPEG key frames on disk. Then:30311. Parse the JSON from stdout.322. Read the `frames[].filePath` images (in parallel) when the question needs visuals.333. Answer from transcript + OCR + frames, citing timestamps.3435Useful flags: `--detail brief|standard|detailed` (brief = metadata + transcript only, no frame extraction — the fast/cheap path), `--fields metadata,transcript` (filters the emitted JSON only; frames are still computed at standard detail), `--max-frames <1-60>`, `--max-width <px>` (frame width cap, default 800; `0` keeps source resolution — use it for dense UI captures whose payload is small text), `--language <code>` (force transcription language), `--out <dir>` (where frames are copied), `--force-refresh`. Run `npx -y mcp-video-analyzer@latest analyze --help` for the full list.3637## Prerequisites & degradation3839- Node.js 22.12+ (required). `ffmpeg` is bundled — no install needed.40- Platform URLs (YouTube, Instagram, TikTok, …) require `yt-dlp` on PATH; direct `.mp4/.webm/.mov` URLs and local files work without it. Loom transcript, metadata, and comments need no `yt-dlp` either. Loom **frames** usually do — Loom serves most videos as separate DASH video+audio streams that only `yt-dlp` fetches and merges; a CDN fallback covers some videos without it.41- The tool never fails on partial results: the `warnings` array carries actionable hints (yt-dlp install, `YTDLP_COOKIES_FROM_BROWSER` for Instagram/age-restricted, missing Whisper backend). Relay relevant warnings to the user instead of treating them as errors.42- An empty transcript alongside a "silent audio" warning means the video genuinely has no speech (common for muted Reels/Stories) — that is content, not a failure.43- Only `http(s)` URLs to **public** addresses are accepted. A URL on `localhost`, a private/LAN range, a `.local` name, a UNC share, or a non-HTTP scheme is rejected up front with a message saying so — that is a deliberate refusal, not a transient error, so do not retry it or try to work around it. When the user really does want a video from their own network, tell them to restart the server with `MCP_ALLOW_PRIVATE_URLS=1`. Cloud metadata endpoints stay blocked even then.
guimatheus92