Makes the video, the images and the audio, and understands the footage it already has.
Built for: The small studio or solo creator producing more media each month than a manual pipeline can carry.
The button opens the checkout, where 7 servers and 4 skills are listed one by one with what each does to the bill — free, already yours, monthly or a one-off licence. Nothing is charged until you confirm it there, in Stripe’s own card frame on that page rather than a redirect, and each paid member keeps its own budget cap.
The reason to buy a stack rather than five listings: each line below needs more than one member connected at the same time.
Transcode and assemble video through an API rather than a local render queue.
Generate images from text and iterate on them without leaving the session.
Watch existing footage — frames and audio — and say what is in it, so an archive becomes searchable.
Drive a game engine or a headless Blender check for the parts of production that are assets rather than clips.
What each part contributes, and why it was picked over the obvious alternative. Prices and permissions are read from the listings, so nothing here can disagree with the catalogue.
Video transcoding as an API call, which is what turns a render queue into a step in a pipeline.
Image generation through Replicate's hosted models, for the visual work that does not need a designer's hand.
Drives the Godot 4.x engine, for studios whose output is interactive rather than linear.
Headless Blender asset QA — reimport verification and background scripts — the check that catches a broken model before it ships in a build.
Extracts frames and audio so existing footage can be described, which is how an archive becomes something you can search.
Structured YouTube data for the published side: what exists, how it is described, and what the metadata actually says.
Text-to-video and image-to-video generation over an OpenAI-compatible API, for the shots that do not need to be filmed.
Ingests video and audio from files, URLs or live feeds and returns real-time context, which is the searchable-library half of a studio.
Video as React — twenty-nine rules covering animation, captions, audio and transitions — for output that has to be produced the same way every week.
Generates MIDI with real music theory behind it, for the soundtrack that would otherwise be a stock loop.
The calendar and the platform-specific plan, so production serves a schedule instead of producing whatever was interesting that week.
Every member is a subscription or a licence bought once, so the monthly figure is a price rather than an estimate: what moves it is adding or dropping a member, not how hard the stack is worked. The one assumption is that a one-off licence is spread over a year so it can sit in the same column as a subscription.
| Part | What you are paying for | Monthly, as quoted |
|---|---|---|
| Ffmpeg Micro | Free | — |
| Replicate Flux | Free | — |
| Godot Mcp Runtime | Free | — |
| Ellmos Blender Use | Free | — |
| Claude Video Vision | from $14/mo | $14/mo |
| YouTube | Free | — |
| Agnes Video | Free | — |
| Skills | ||
| VideoDB | $24 · $2.00/mo over 12 months | $2.00/mo |
| Remotion Video Creation | $35 · $2.92/mo over 12 months | $2.92/mo |
| MIDI Generation | $39 · $3.25/mo over 12 months | $3.25/mo |
| Social Media Strategy | Free · context cost only | — |
| Everything above | $14 of servers plus $8.00 of skills, the same in a quiet month and a busy one | $22/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. One-off purchases in this stack total $98 — VideoDB $24, Remotion Video Creation $35, MIDI Generation $39 — paid once and spread here so they sit in the same column as a subscription. Everything arrives on one mcprush invoice, taken by Stripe from the card on your account, not one per publisher — mcprush.com is the merchant of record and each publisher is paid out of it.
Install only these and the bill is nothing: 6 servers and 1 skill, 0 of the 6 tools.
Left out, and what goes with it:
Claude Video Vision at from $14/mo. Each of those plans states the calls it includes in a month, and running past one never arrives as a larger invoice: the gateway refuses the call over the allowance and returns an MCP error naming the plan. The figure above is what the stack costs in a busy month as well as a quiet one — what a heavy month changes is which plan you need, not what this one bills.
Budget caps are set per install and enforced at the gateway, so a retry loop is refused at the cap rather than left to run through an allowance overnight.
One step per part, in the order they are useful: connect what the work reads before what it writes, and install the skills that decide how the work is done last. Each step is a command you can read before you run it.
npx mcprush@latest stack add media-studioNothing in this stack installs from one command today: 11 members are either paid, run from its own source, or a skill with its own command — the steps above name each one. Nothing is connected until you approve it.
Installed together, these tool surfaces add up. It is the first thing a security reviewer asks for, so what has been counted — and what nobody has counted yet — is on the page rather than in a PDF.
| Member | Tool surface | Write tools |
|---|---|---|
| Agnes Video | not imported | not recorded |
| Ellmos Blender Use | not imported | not recorded |
| Ffmpeg Micro | not imported | not recorded |
| Godot Mcp Runtime | not imported | not recorded |
| Replicate Flux | not imported | not recorded |
| YouTube | not imported | not recorded |
A stack's blast radius is the union of its members, not the worst of them. That union cannot be taken here, because 6 members of 7 have no imported tool surface — so the figure a review asks for is missing rather than low, and a member marked not imported is one nobody has counted rather than one that cannot write.
A stack is a default, not a verdict. These are the substitutions the maintainer would make, and what each one costs or saves.
A different generation backend with a different look and a different bill; keep the one whose output you actually ship.
The same generated-shot job through another provider, for teams whose access is there rather than to an OpenAI-compatible endpoint.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot clear rights. Generated and ingested media carry licence questions this stack does not answer.
It does not publish on its own. YouTube here is read: metadata and data, not uploads under your name.
Render costs are real. Every video and image member bills per job, and a revision loop is the fastest way to spend a month's budget.
A stack has an owner: whoever keeps it re-checks the combination when a member changes, and the members themselves are published by the people named on each row.
Reads the branch, runs it in a throwaway sandbox, and leaves the review on the merge request before a human opens it.
Turns a bug report into a reproduction that fails, before anybody writes a line of the fix.
Answers the page: what fired, what changed, what the runbook says, and what to tell the channel.