Name: Video Analyzer
Price: 9 USD
Author: BrightWayAI

93/100

trust score

downloads a day

remote

via our gateway

167

downloads in 30d

What it does

🎬 Paste a video link. Get the whole storyboard back.

Hand your AI assistant a YouTube, Shorts, TikTok or direct video link and say "break this down." Video Analyzer watches it the way an editor would: it finds every cut, looks at each shot with Claude Vision, reads the text on screen, transcribes the speech, times the edit, and returns a complete shot-by-shot breakdown you can read, reuse or recreate.

🖼️ What one call gives you

Shot-by-shot storyboard: every scene with its timestamp, its frame, a production-ready visual description, the on-screen text and the line spoken over it
⏱️ Pacing & hook: cuts per minute, shot lengths, time to the first cut, words per minute, and exactly what happens in the first 3 seconds
🔤 On-screen text: captions, titles and stickers read off every shot, word for word
🧬 Stylistic Fingerprint: eight labels that pin down the look and feel (rendering, world, characters, narrative, abstraction, density, editing, tone)
📄 PDF storyboard ready to send to a client, plus a Word file, a contact sheet of every shot and a zip of every frame

🆚 New: compare two videos

Give it your video and the one that went viral. You get both breakdowns side by side, every difference flagged, and a written read on what each does better and what to borrow.

🔍 Real output, not a mock-up

A 10-second TikTok pet video → 19 shots. 102.9 cuts/min · 0.55s average shot · first cut at 0.5s · 6 shots in the first 3s. On-screen text picked up: COOLING CHILLY PAD TOWEL. Fingerprint: Live Action · Mascot-Led · Social Vertical Punch.

Compared with the Big Buck Bunny trailer, it flagged the trailer's 3.5-second opening title card and suggested: "Cut the opening 3s presenter card, or shrink it to under 1s, and start on the rabbit standing in the meadow."

💡 Built for

Creators and social teams reverse-engineering why a format works: pacing, framing, hooks, captions, tone
Explainer studios and instructional designers matching a reference style shot for shot
Agencies turning competitor and inspiration videos into creative briefs, mood boards and client-ready PDFs
Anyone using AI image or video tools: every shot description doubles as a ready-made generation prompt

⚙️ Five tools

video_analyze: the full breakdown (storyboard, pacing & hook, fingerprint, PDF and files)
video_compare: two videos side by side, with what to borrow
video_extract_frames: just the shots, their frames and the pacing, fast, no AI write-up
video_transcribe: a timestamped transcript
video_fingerprint: just the style classification and pacing

✅ Good to know

Nothing to install. No API keys, no FFmpeg, no Python: it all runs on our server.
A short video takes about a minute. Your assistant gets a "still working" note and simply asks again; those check-ins never count against your plan.
Files stay downloadable for 72 hours: the PDF, the .docx, the contact sheet and the frames.
Public videos only. If a site refuses the download, a direct link to the video file always works.

Quickstart

# 1 — buy it first ($9 a month): mcprush.com/checkout?server=brightwayai-video-analyzer-mcp
#     a key alone is not enough: the gateway refuses every call until it is bought
# 2 — sign in with a key of the account that bought it: npx mcprush@latest login
#     the key is at mcprush.com/dashboard#access
# 3 — install
npx mcprush@latest add brightwayai/video-analyzer-mcp

# 4 — ask your agent for something these tools do
#   video_analyze, video_extract_frames, video_transcribe and 2 more

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither.

Publisher

BrightWayAI1 server

1 category · publishing since 2026

All 1 server

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.

Claude Codedeclared by this listing

Claude Code has its own MCP command, and the key rides on it as a header — the gateway refuses a call that carries none. Claude Code reads MCPRUSH_KEY each time it connects, so the key stays out of its config: export your key from Access in your shell profile (macOS, Linux), or run setx MCPRUSH_KEY <your key> and open a new terminal (Windows). Or let npx mcprush@latest add brightwayai/video-analyzer-mcp write the entry with the key for you; --scope user makes it available in every project.

Buy it first — $9 a month. A key alone is not enough: until this account has bought it, the gateway refuses every call. Subscribe, then use a key of the account that bought it.

claude mcp add --transport http --scope user brightwayai-video-analyzer-mcp https://mcprush.com/gw/brightwayai-video-analyzer-mcp/mcp --header 'Authorization: Bearer ${MCPRUSH_KEY}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

This is a paid listing: the gateway answers only a key of an account whose subscription to it is active — how the login works. Until then add writes nothing: signed out, it names the price and the checkout link; signed in, it prints the checkout link, or why the subscription is held (ended, paused, an unpaid invoice) and the link that lifts it. The gateway refuses every call the same way, and most clients only show the server as failed.

What it writes

One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.

What you approve

5 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Run the full video analysis pipeline: download, extract frames, transcribe audio, analyze visuals with Claude, generate the stylistic fingerprint, and produce a shot-by-shot storyboard. On the hosted server the result is a summary (with the fingerprint and links to the Word storyboard, frame images and a zip of all frames), the storyboard as Markdown, and a contact-sheet image

Parameter	Type	Required	Notes
params		yes	—

Extract representative frames from a video using scene detection or fixed intervals. Uses PySceneDetect to find scene boundaries, then extracts the middle frame of each scene. Falls back to 3-second intervals if no scenes are detected. Returns the shots with timestamps. On the hosted server each shot has a frame_url, and the result includes a contact-sheet image and a zip lin

Parameter	Type	Required	Notes
params		yes	—

Transcribe the audio track of a video using OpenAI Whisper (runs locally, no OpenAI key needed). Returns timestamped transcript segments with inferred speaker labels (NARRATOR, TEACHER, CHILD, SPEAKER). 'base' is fastest; 'large' is most accurate (the hosted server offers 'base' and 'small').

Parameter	Type	Required	Notes
params		yes	—

Generate a Stylistic Fingerprint (v3) for a video. Performs frame extraction, transcription, and visual analysis, then runs the deterministic fingerprint classifier to produce 8 classification fields: 1. Rendering Class (e.g., Stylized 3D, Flat 2D, Mixed Media) 2. World Type (e.g., Stylized Real-World, Abstract Concept Space) 3. Character Strategy (e.g., Mascot-Led, Single Na

Parameter	Type	Required	Notes
params		yes	—

Compare two videos side by side: style fingerprint, pacing, hook and story structure, plus a written breakdown of the biggest differences and what each video could borrow from the other. Good for "my video vs. the one that went viral", or matching a reference. Both videos are fully analyzed, so links to each one's PDF storyboard come back too. Takes a few minutes.

No parameter schema on file.

Starter

$9 / month

10 calls a month, included
6 calls a minute at peak
Every tool the listing has
Cancel any time — the unused days are credited
Runs behind the gateway, so cancelling stops it

What counts against the 10 calls a month on Starter

Tool	Unit	Calls used	Out of the monthly allowance
video_analyze	write	2	20.0000%
video_extract_frames	write	2	20.0000%
video_transcribe	call	1	10.0000%
video_fingerprint	call	1	10.0000%
video_compare	write	2	20.0000%

Failed calls, timeouts and anything the gateway rejects never count. When the allowance runs out the gateway returns an error naming the plan limit — nothing is billed beyond the subscription, ever.

ATrust score 93 / 100

Scanned: 0.1.2 · 11 Nov 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings1 threat · 1 capability

Capabilityhigh

Coveragesource

Verificationrepo

Surface digest0c2be3812ab05970139e7871d9899dcbdcf36143b6b9ffe3cdb5286eb87ed4a9

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	high	capability blast radius (high) — client exposure if the model is manipulated	−6
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.

Tool	Capability tags	Why the tag was assigned
video_extract_frames	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
video_transcribe	no tags
video_fingerprint	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
video_check_deps	no tags
video_analyze	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest0c2be3812ab05970

Scanned2026-11-11

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Video Analyzer MCP