Envie

Your AI writes HTML; Envie renders it to video on your machine, verifies it and shows it back.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.

Manual Client & Custom JSON ConfigExpand JSON ▾

No confirmed setup config for this listing yet. We only publish a config block when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for Envie, and we’d rather show nothing than a guess you’d paste into your client. Follow the project’s own setup instructions for the current steps.

Documentation Overview

Envie

AI video, verified.

Describe a video to your AI. Get a real file back.

Envie gives Claude Code and any MCP client a deterministic render engine: headless Chrome filmed frame by frame, six verification gates, and a full read-back layer. Free. No watermark. No account.

By GOL Productions.

The Problem

AI can write code. AI can describe video. But AI can't see what it made—so it guesses, you render, it's wrong, you describe what's wrong, repeat.

The Solution

Code

You: "Make me a 15-second launch video for my app"
AI:  [writes HTML composition]
AI:  [calls envie_render]
AI:  [calls envie_see to check frames]
AI:  "Done. Video at output.mp4. All 6 gates passed."

Envie renders what your AI writes, verifies it machine-checks, and lets your AI see the result. No guessing.

Install

Terminal

npx @golproductions/envie@latest setup

Detects Claude Code, Cursor, Windsurf—registers with all of them. Then just ask:

"Make me a 15-second vertical launch video for my app"

Manual install

config.json

{ "mcpServers": { "envie": { "command": "npx", "args": ["-y", "@golproductions/envie", "mcp"] } } }

Or for Claude Code:

Terminal

claude mcp add --scope user envie -- npx -y @golproductions/envie mcp

How It Works

Code

┌─────────────┐     ┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│   WRITE     │ ──► │   RENDER    │ ──► │   VERIFY    │ ──► │    SEE      │
│             │     │             │     │             │     │             │
│ AI writes   │     │ Chrome films│     │ 6 gates     │     │ AI checks   │
│ HTML comp   │     │ frame by    │     │ machine-    │     │ frames at   │
│             │     │ frame       │     │ check video │     │ timestamps  │
└─────────────┘     └─────────────┘     └─────────────┘     └─────────────┘

1. Write

Your AI reads envie_guide and writes a composition: one self-contained HTML file with CSS animations, WebGL, Canvas, GIFs—whatever the browser can render.

2. Render

envie_render films it deterministically. Headless Chrome with a virtualized clock: performance.now(), Date.now(), requestAnimationFrame, setTimeout—all seeked frame by frame.

Same composition = same video. Every time.

3. Verify

Six gates machine-check the result before delivery:

Gate	What it checks
G1	File exists, valid container, ≥2.9s duration
G2	Has both video and audio streams
G3	Audio isn't silent (mean > -50dB)
G4	No black segment > 2 seconds
G5	No freeze > 8 seconds, < 60% total still time
G6	Final 15% isn't dead (frozen or black)

A failing video comes back marked FAILED, with the gate report and an instruction not to deliver it, so your AI fixes the composition and renders again.

4. See

envie_see returns frames at chosen timestamps so your AI can judge layout and pacing—not just whether the file exists.

5. Translate

envie_translate reads the finished file as data: per-frame motion, every cut and fade, still holds, LUFS, true peak, and how each audio hit sits against the nearest picture event.

Requirements

Requirement	Notes
Node 24+	Or later
Chrome	Or set `ENVIE_CHROME` to your binary
ffmpeg + ffprobe	Must be on PATH
Audio	Required. Videos with no audio fail G2 and G3

Audio options

Option	Platform	Description
`--narration "text"`	Windows only	Local TTS voiceover (SAPI)
`--audio file.wav`	All platforms	Overlay any wav/mp3/m4a

Runs entirely on your machine. Nothing reaches GOL servers.

Formats

Flag	Container	Codec
`--format h264`	.mp4	libx264 (default)
`--format h265`	.mp4	libx265 10-bit
`--format prores`	.mov	ProRes 422 HQ 10-bit
`--format prores4444`	.mov	ProRes 4444 10-bit
`--format dnxhr`	.mov	DNxHR HQ

CLI

Terminal

npx @golproductions/envie@latest setup                   # register MCP server
npx @golproductions/envie@latest uninstall               # remove everything Envie added
envie render <comp.html> -o out.mp4 [options]            # render video
envie see    <comp.html|video.mp4> [--at 1000,4000]      # extract frames
envie verify <video.mp4>                                 # run gates
envie translate <video.mp4>                              # analyze motion/audio
envie guide                                              # print authoring guide
envie mcp                                                # start MCP server

envie here means npx @golproductions/envie@latest. Use @latest: plain npx runs an older globally installed copy if one exists.

Render options

Code

--narration "text"     # TTS voiceover (Windows)
--audio file.wav       # Overlay audio file
--fps 24               # Frame rate (default: 24)
--format h264          # Output codec
-o output.mp4          # Output path

Composition Format

One self-contained HTML file:

html

<!DOCTYPE html>
<html>
<head>
<style>
  body { margin: 0; width: 1080px; height: 1920px; overflow: hidden; }
  /* your animations */
</style>
</head>
<body data-duration-ms="15000" data-width="1080" data-height="1920">
  <!-- your content -->
</body>
</html>

Required attributes

Attribute	Description
`data-duration-ms`	Video length in milliseconds (3000–300000)
`data-width`	Canvas width (default: 1920)
`data-height`	Canvas height (default: 1080)

What's virtualized

Everything the browser can animate:

CSS animations, transitions
Web Animations API
requestAnimationFrame
setTimeout, setInterval
Canvas 2D, WebGL
performance.now(), Date.now(), new Date()
Animated images (GIF, WebP, APNG, AVIF)
Math.random(), crypto.getRandomValues (seeded)
Classic Web Workers (run on the virtual clock)

NOT virtualized (avoid):

Module Web Workers and strict-mode worker code
WebAudio-driven visuals

Intent Assertions

Declare what the composition must achieve:

html

<body data-duration-ms="12000"
      data-expect-sync-ms="120"
      data-expect-no-holds-longer-than="3">

Assertion	Meaning
`data-expect-sync-ms="120"`	Audio hits must land within 120ms of a picture event
`data-expect-no-holds-longer-than="3"`	No still hold may exceed 3 seconds

Failures are reported test-style:

Code

SYNC FAIL: mean audio-to-picture offset 380ms exceeds tolerance 120ms
HOLD FAIL: 2 hold(s) exceed 3s: 4.20s @0.40s, 3.10s @7.80s

Deterministic Rendering

The render engine virtualizes time itself:

javascript

// Inside the page during render:
performance.now()  // → virtual clock
Date.now()         // → virtual clock
new Date()         // → virtual clock
Math.random()      // → seeded PRNG

// Same seed, same composition = identical output

This is how the same HTML produces the same video, every render.

What "deterministic" means

Same machine + same Chrome version + same composition = bit-identical output.

Cross-environment, you may see variation from:

Font rendering (anti-aliasing, hinting differ by OS/GPU)
WebGL/Canvas floating-point precision
Chrome version changes
System font fallbacks (embed fonts to avoid)

The guarantee is reproducibility on your machine, not cross-platform bit-identity. That's the right scope: your AI iterates locally, re-renders, gets the same result.

Your Work Is Yours

GOL claims no ownership over your compositions or videos. Envie runs on your machine. Nothing you make reaches us.

License

Free to use, personal or commercial, under the GOL Free License. Envie is built by GOL Productions: you may use it and share unmodified copies with the credit, but not publish changed versions, build your own product from it, or sell it. What you make with it is yours. See LICENSE.

GOL Productions

Envie is part of the GOL Productions toolchain.

Check — Anti-hallucination layer for Claude Code
Exnos — Live browser verification

Product page · GitHub

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives

Reviews

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

Frequently Asked Questions about Envie

We don't have a confirmed install command for Envie yet, so we don't publish a generated one — a guessed package name would point at the wrong package or none at all. Follow the project's own README or setup instructions (https://github.com/golproductions/envie) for the current steps.

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 Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/envie?style=directory)](https://allmcps.com/mcp/envie)

HTML Embed

<a href="https://allmcps.com/mcp/envie"><img src="https://allmcps.com/api/badge/envie?style=directory" alt="Envie on AllMCPs" /></a>

Technical Specs & Signals

CategoryDeveloper Tools

27Quality signal: Emerging · 27/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20

Documentation & tools11/30

Adoption & activity1/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to Envie →Install in Claude Desktop Install in Cursor Install in VS Code Setup guides for all 13 MCP clients

Envie

Your AI writes HTML; Envie renders it to video on your machine, verifies it and shows it back.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Manual Client & Custom JSON ConfigExpand JSON ▾

Documentation Overview

Envie

AI video, verified.

Describe a video to your AI. Get a real file back.

Envie gives Claude Code and any MCP client a deterministic render engine: headless Chrome filmed frame by frame, six verification gates, and a full read-back layer. Free. No watermark. No account.

By GOL Productions.

The Problem

AI can write code. AI can describe video. But AI can't see what it made—so it guesses, you render, it's wrong, you describe what's wrong, repeat.

The Solution

Code

You: "Make me a 15-second launch video for my app"
AI:  [writes HTML composition]
AI:  [calls envie_render]
AI:  [calls envie_see to check frames]
AI:  "Done. Video at output.mp4. All 6 gates passed."

Envie renders what your AI writes, verifies it machine-checks, and lets your AI see the result. No guessing.

Install

Terminal

npx @golproductions/envie@latest setup

Detects Claude Code, Cursor, Windsurf—registers with all of them. Then just ask:

"Make me a 15-second vertical launch video for my app"

Manual install

config.json

{ "mcpServers": { "envie": { "command": "npx", "args": ["-y", "@golproductions/envie", "mcp"] } } }

Or for Claude Code:

Terminal

claude mcp add --scope user envie -- npx -y @golproductions/envie mcp

How It Works

Code

┌─────────────┐     ┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│   WRITE     │ ──► │   RENDER    │ ──► │   VERIFY    │ ──► │    SEE      │
│             │     │             │     │             │     │             │
│ AI writes   │     │ Chrome films│     │ 6 gates     │     │ AI checks   │
│ HTML comp   │     │ frame by    │     │ machine-    │     │ frames at   │
│             │     │ frame       │     │ check video │     │ timestamps  │
└─────────────┘     └─────────────┘     └─────────────┘     └─────────────┘

1. Write

Your AI reads envie_guide and writes a composition: one self-contained HTML file with CSS animations, WebGL, Canvas, GIFs—whatever the browser can render.

2. Render

envie_render films it deterministically. Headless Chrome with a virtualized clock: performance.now(), Date.now(), requestAnimationFrame, setTimeout—all seeked frame by frame.

Same composition = same video. Every time.

3. Verify

Six gates machine-check the result before delivery:

Gate	What it checks
G1	File exists, valid container, ≥2.9s duration
G2	Has both video and audio streams
G3	Audio isn't silent (mean > -50dB)
G4	No black segment > 2 seconds
G5	No freeze > 8 seconds, < 60% total still time
G6	Final 15% isn't dead (frozen or black)

A failing video comes back marked FAILED, with the gate report and an instruction not to deliver it, so your AI fixes the composition and renders again.

4. See

envie_see returns frames at chosen timestamps so your AI can judge layout and pacing—not just whether the file exists.

5. Translate

envie_translate reads the finished file as data: per-frame motion, every cut and fade, still holds, LUFS, true peak, and how each audio hit sits against the nearest picture event.

Requirements

Requirement	Notes
Node 24+	Or later
Chrome	Or set `ENVIE_CHROME` to your binary
ffmpeg + ffprobe	Must be on PATH
Audio	Required. Videos with no audio fail G2 and G3

Audio options

Option	Platform	Description
`--narration "text"`	Windows only	Local TTS voiceover (SAPI)
`--audio file.wav`	All platforms	Overlay any wav/mp3/m4a

Runs entirely on your machine. Nothing reaches GOL servers.

Formats

Flag	Container	Codec
`--format h264`	.mp4	libx264 (default)
`--format h265`	.mp4	libx265 10-bit
`--format prores`	.mov	ProRes 422 HQ 10-bit
`--format prores4444`	.mov	ProRes 4444 10-bit
`--format dnxhr`	.mov	DNxHR HQ

CLI

Terminal

npx @golproductions/envie@latest setup                   # register MCP server
npx @golproductions/envie@latest uninstall               # remove everything Envie added
envie render <comp.html> -o out.mp4 [options]            # render video
envie see    <comp.html|video.mp4> [--at 1000,4000]      # extract frames
envie verify <video.mp4>                                 # run gates
envie translate <video.mp4>                              # analyze motion/audio
envie guide                                              # print authoring guide
envie mcp                                                # start MCP server

envie here means npx @golproductions/envie@latest. Use @latest: plain npx runs an older globally installed copy if one exists.

Render options

Code

--narration "text"     # TTS voiceover (Windows)
--audio file.wav       # Overlay audio file
--fps 24               # Frame rate (default: 24)
--format h264          # Output codec
-o output.mp4          # Output path

Composition Format

One self-contained HTML file:

html

<!DOCTYPE html>
<html>
<head>
<style>
  body { margin: 0; width: 1080px; height: 1920px; overflow: hidden; }
  /* your animations */
</style>
</head>
<body data-duration-ms="15000" data-width="1080" data-height="1920">
  <!-- your content -->
</body>
</html>

Required attributes

Attribute	Description
`data-duration-ms`	Video length in milliseconds (3000–300000)
`data-width`	Canvas width (default: 1920)
`data-height`	Canvas height (default: 1080)

What's virtualized

Everything the browser can animate:

CSS animations, transitions
Web Animations API
requestAnimationFrame
setTimeout, setInterval
Canvas 2D, WebGL
performance.now(), Date.now(), new Date()
Animated images (GIF, WebP, APNG, AVIF)
Math.random(), crypto.getRandomValues (seeded)
Classic Web Workers (run on the virtual clock)

NOT virtualized (avoid):

Module Web Workers and strict-mode worker code
WebAudio-driven visuals

Intent Assertions

Declare what the composition must achieve:

html

<body data-duration-ms="12000"
      data-expect-sync-ms="120"
      data-expect-no-holds-longer-than="3">

Assertion	Meaning
`data-expect-sync-ms="120"`	Audio hits must land within 120ms of a picture event
`data-expect-no-holds-longer-than="3"`	No still hold may exceed 3 seconds

Failures are reported test-style:

Code

SYNC FAIL: mean audio-to-picture offset 380ms exceeds tolerance 120ms
HOLD FAIL: 2 hold(s) exceed 3s: 4.20s @0.40s, 3.10s @7.80s

Deterministic Rendering

The render engine virtualizes time itself:

javascript

// Inside the page during render:
performance.now()  // → virtual clock
Date.now()         // → virtual clock
new Date()         // → virtual clock
Math.random()      // → seeded PRNG

// Same seed, same composition = identical output

This is how the same HTML produces the same video, every render.

What "deterministic" means

Same machine + same Chrome version + same composition = bit-identical output.

Cross-environment, you may see variation from:

Font rendering (anti-aliasing, hinting differ by OS/GPU)
WebGL/Canvas floating-point precision
Chrome version changes
System font fallbacks (embed fonts to avoid)

The guarantee is reproducibility on your machine, not cross-platform bit-identity. That's the right scope: your AI iterates locally, re-renders, gets the same result.

Your Work Is Yours

GOL claims no ownership over your compositions or videos. Envie runs on your machine. Nothing you make reaches us.

License

GOL Productions

Envie is part of the GOL Productions toolchain.

Check — Anti-hallucination layer for Claude Code
Exnos — Live browser verification

Product page · GitHub

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives

Reviews

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

Frequently Asked Questions about Envie

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 Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/envie?style=directory)](https://allmcps.com/mcp/envie)

HTML Embed

<a href="https://allmcps.com/mcp/envie"><img src="https://allmcps.com/api/badge/envie?style=directory" alt="Envie on AllMCPs" /></a>

Technical Specs & Signals

CategoryDeveloper Tools

27Quality signal: Emerging · 27/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20

Documentation & tools11/30

Adoption & activity1/15

Community engagement0/10

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to Envie →Install in Claude Desktop Install in Cursor Install in VS Code Setup guides for all 13 MCP clients