video-mcp
Uses ElevenLabs text-to-speech to generate narration audio for video segments, with configurable voice and delivery settings.
Produces videos in YouTube explainer format (16:9) suitable for YouTube content.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
video-mcp
An MCP server that turns a script into a narrated video. Point an AI agent at it and it can produce YouTube explainers (16:9) or Reels/Shorts (9:16) from three kinds of source:
Engine | Tool | You supply | Good for |
HTML scroll |
| An HTML page + segments naming a CSS selector each | Long-form explainers, docs walkthroughs, architecture pages |
Remotion |
| JSON props for a built-in template, or your own React component | Slide-style reels, data callouts, anything you'd design in React |
HyperFrames |
| A folder with | Kinetic-caption reels, motion-graphics styles you iterate on as code |
The idea shared by all three: narration is generated first, and its real duration drives the visuals. Each segment gets the exact on-screen time its voice-over takes, so timing never drifts. Captions come from the same timestamps for free.
Requirements
Node 20+
ffmpegandffprobeonPATHAn ElevenLabs API key for narration
Chromium for Playwright (
npx playwright install chromium; Remotion downloads its own)
Related MCP server: Remotion Video Production MCP Server
Quickstart
git clone https://github.com/techbysaurabh/video-mcp && cd video-mcp
npm install && npx playwright install chromium
cp .env.example .env # add ELEVENLABS_API_KEY
npm run demo:html # silent render of the example page, no keys needed
npm start # MCP over HTTP at http://127.0.0.1:3100/mcpOr with Docker (Chromium and ffmpeg included):
docker build -t video-mcp . && docker run -p 3100:3100 -e ELEVENLABS_API_KEY=... -v $PWD/output:/data/output video-mcpConnect a client
Claude Code, HTTP:
claude mcp add --transport http video-mcp http://127.0.0.1:3100/mcpClaude Code, stdio (the client spawns the server; no port):
claude mcp add video-mcp -e ELEVENLABS_API_KEY=... -- node /path/to/video-mcp/src/mcp/server.js --stdioCursor (.cursor/mcp.json):
{ "mcpServers": { "video-mcp": { "url": "http://127.0.0.1:3100/mcp" } } }First video
Ask your agent:
Use video-mcp to render the bundled example with
generate_video, then pollget_job_statusuntil it's done and tell me where the MP4 is.
That renders examples/html-scroll/page.html with the five segments in segments.json, and writes
output/<job>/output.mp4 plus captions.srt.
Tools
Tool | Purpose |
| HTML scroll engine. |
| Remotion engine. |
| HyperFrames engine. |
| TTS only; returns each segment's duration so you can tune the script before rendering |
| Screenshot an HTML page at given timestamps to check scroll targets |
| Renders are async; poll here. Results carry |
| Props accepted by the built-in compositions |
How it works
segments ──▶ ElevenLabs TTS (cached by voice+text) ──▶ narration.mp3 + per-segment timestamps
│
┌───────────────────────────────────────────────────┼──────────────────────────────┐
▼ ▼ ▼
HTML: Playwright scrolls to each Remotion: props get startTime/ HyperFrames: compose() gets
scrollSelector on the timestamps, duration, React renders to MP4 timed segments, emits HTML+GSAP,
screenshots at 24 fps hyperframes renders it
└───────────────────────────────────────────────────┴──────────────────────────────┘
│
ffmpeg mux (video + narration) + SRT ──▶ output/<job>/output.mp4
│
optional S3 upload (AWS_S3_BUCKET set)Details worth knowing:
TTS cache. Audio is cached by
sha256(voiceId + text); unchanged segments cost nothing on re-render.Scroll motion. Between segments the page eases to the next target over 0.6 s and holds. The
mobilelayout renders a 390 px CSS viewport scaled to 1080×1920 so responsive breakpoints kick in.Remotion custom mode.
jsx_codeis written to a per-job entry and bundled; the component receives{segments, timestamps, totalDuration, ...props}with each segment'sstartTimeanddurationresolved.HyperFrames styles.
compose.mjsexports({ segments, totalDuration, media, narration }) => html. Segments arrive with timing filled in;media[id]describes files a segment referenced vialocalMedia. Seeexamples/hyperframes-kineticfor a caption style that splits each sentence into beats weighted by length.Muxing. Remotion emits a silent AAC track; the mux maps
0:v:0and1:a:0explicitly so the narration always wins.Cost guard.
cost_ceil_chars(default 50 000) aborts a job before any TTS is spent.
Configuration
Variable | Default | Meaning |
| Required for narration | |
|
| Default voice |
|
| Delivery tuning |
|
| HTTP mode bind |
|
| Where jobs write |
| Optional upload; results then include | |
|
| Pinned |
CLI helpers
npm run demo:html # silent scroll render of the example page (no keys)
npm run demo:remotion # silent SegmentReel render (no keys)
npm run render:hyperframes -- examples/hyperframes-kinetic # full narrated render
npm testScope
This repo is the rendering core: narration, three engines, muxing, captions, optional upload, exposed over MCP. Publishing to platforms, AI-generated imagery, avatars and brand kits are deliberately out of scope; build them on top.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate images, GIFs, videos, and PDFs from HTML, URLs, or templates — from your AI agent.
AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.
AI video agent: edit timelines, captions, voice, music, images and ads, then render MP4s.
Video, image and audio generation on top AI models for agents, with an AI director built in.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to generate narrated videos from topics or scripts, with stock footage, home videos, or local AI clips.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to programmatically scaffold Remotion projects, analyze audio for beat-synced scenes, synthesize voiceovers with word-level timecodes, preview frames, and render finished videos.20 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to create polished product demo videos by controlling a real Chromium browser, recording actions, and rendering 1080p MP4s with narration, captions, and styled overlays.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate complete short-form videos from text prompts, combining text-to-speech, automatic captions, background footage, and music.MIT