short-video-maker MCP
An MCP server and REST API to assemble short vertical videos with captions, voiceover and music for TikTok, Reels and Shorts
- 1,491 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs a local service and renders video
- Calls a stock service with a key
Install
- Works in
Manual install
docker run -it --rm --name short-video-maker -p 3123:3123 -e PEXELS_API_KEY= gyoridavid/short-video-maker:latest-tinySet your free Pexels key; latest and latest-cuda images are available for GPU.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs a local service and renders video
- Calls a stock service with a key
This is third-party code. Review the repository files before installing.
What it does
The project assembles short videos from text: it adds voiceover, captions, stock background clips and music and renders a finished vertical clip. It works as an MCP server and as a REST API, so it can connect to an agent or fit into your own automation. Background clips come from a stock service via a free key, while speech recognition and rendering run locally. Docker is the recommended way to run it, with CPU and GPU variants, and npm installation is also available.
Who it is for. For content people and marketers who need to produce short clips at scale.
Good fit when
- You need to assemble a short video from text with captions and voiceover
- You need to automate clip production via an agent or a script
- You need local rendering without a paid video editor
Not a fit when
- You need complex editing with manual frame control
- You lack resources for local video rendering
Example request
Assemble a short vertical video from this text with captions and background musicMCP
- Transport
- sse
- Authentication
- not required
Environment variables
PEXELS_API_KEYrequired, secret- Free Pexels stock key for background clips
Limitations
Rendering and speech recognition need machine resources. A free Pexels stock key is required for background clips, and its availability from Russia should be checked. The final video is assembled from templates, so fine manual editing is limited.
How to disable. Stop and remove the short-video-maker container or uninstall the npm package.
FAQ
MCP or REST?
There is both an MCP server for the agent and a REST API. REST gives more flexibility for video generation.
Do I need paid access?
No, you need a free Pexels stock key; speech recognition and rendering run locally.
Discussion
No questions or reviews yet.
Related
MCP serversMCP server, CLI and desktop app that cut a long video or stream replay into vertical clips with captions
ClipForge MCP
ClipForge
ClipForge MCP builds a vertical video from a topic or a product link: stock footage, Edge TTS voiceover and captions, no keys, composed with FFmpeg
An MCP server with 59 tools for CapCut and OpenCut editing: tracks, clips, text, transitions and voiceover from Cursor and Codex.
A skill and MCP server for cutting long videos: the agent takes a link or file and builds Shorts, Reels and TikTok clips with a cover, post text and ZIP
VidMoat MCP
Vidmoat MCP
Remote MCP server of a cloud video editor: an agent imports footage, edits the timeline, checks frames and renders MP4
Local video editing for agents: typed tools over FFmpeg, quality checks and a provenance receipt before you publish
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| short-video-maker (this card) | no | not required | 1,491 | |
| ClipForge MCP | yes | not required | 1,272 | ClipForge MCP builds a vertical video from a topic or a product link |
| AI Promo Video Maker | no | 469 | a skill for Cursor | |
| Clipcat Skill | no | 505 | the clipcat skill and CLI help a TikTok Shop seller find videos that |
README in short
The README describes short-video-maker as a server that assembles short videos with captions, voiceover and music and exposes both MCP and a REST API. The recommended run is via Docker, with images for the normal mode, low-end machines and GPU, plus npm installation. Background clips need a free Pexels key, and speech recognition uses whisper. It gives REST call examples and the MCP path.