GraphCanon updated 4w · GitHub synced 4w
Decision brief
Short-video-maker is a TypeScript-driven tool to automate the creation of short videos for social media platforms like TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) via its REST API.
Good fit when
- Use it if your project requires automated video generation tailored specifically for popular social media formats such as TikTok or Instagram Reels with precise control over content through MCP.
- Consider this tool when you need a flexible and customizable solution written in TypeScript for generating short videos that integrate seamlessly with modern web applications via RESTful services.
Avoid when
- Avoid if your requirement is focused on desktop application integration or platforms other than the social media formats mentioned, as it may lack the necessary integrations.
- Do not use this tool if you are developing a solution that does not align with TypeScript coding standards or does not benefit from REST API operations for video content creation.
- Requirements:
- The tool is based on TypeScript and requires a REST API to function.; Knowledge of social media platforms' content requirements, such as TikTok or Instagram Reels, will be beneficial.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (1,250) are secondary evidence.
- npm downloads (30d)
- 408·npm downloads API·4w
- Docker Hub pulls (30d)
- 47,893·Docker Hub API·4w
Maintenance and security
Full trust report- Maintenance
- Dormant (400d since push)
- As of 4w
- Provenance
- Not a fork · Personal account
- As of 4w
- Security (OSV)
- No MCP manifest
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install short-video-makerSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Short-video-maker is a TypeScript-based repository for generating short videos tailored for TikTok, Instagram Reels and YouTube Shorts platforms using MCP and a REST API
Capability facts
- Deploy
- Self-host
Source: dockerfile:docker-compose.yml · Jul 27, 2026
- Docker
- Dockerfile present
Source: dockerfile:docker-compose.yml · Jul 27, 2026
- CLI
- CLI entrypoint
Source: package.json:bin|scripts · Jul 27, 2026
- MCP server
- Ships MCP server
Source: package.json:@modelcontextprotocol/* · Jul 27, 2026
- Languages
- typescript, javascript
Source: github.language+package.json · Jul 27, 2026
Categories
Tags
README
Getting started
- Requirements
- How to run the server
- Web UI
- Tutorial
- Examples
General Requirements
- internet
- free pexels api key
- ≥ 3 gb free RAM, my recommendation is 4gb RAM
- ≥ 2 vCPU
- ≥ 5gb disc space
Docker (recommended)
There are three docker images, for three different use cases. Generally speaking, most of the time you want to spin up the tiny one.
Docker compose
You might use Docker Compose to run n8n or other services, and you want to combine them. Make sure you add the shared network to the service configuration.
version: "3"
services:
short-video-maker:
image: gyoridavid/short-video-maker:latest-tiny
environment:
- LOG_LEVEL=debug
- PEXELS_API_KEY=
ports:
- "3123:3123"
volumes:
- ./videos:/app/data/videos # expose the generated videos
If you are using the Self-hosted AI starter kit you want to add networks: ['demo'] to the** short-video-maker service so you can reach it with http://short-video-maker:3123 in n8n.
Docker
The server needs at least 3gb free memory. Make sure to allocate enough RAM to Docker.
If you are running the server from Windows and via wsl2, you need to set the resource limits from the wsl utility 2 - otherwise set it from Docker Desktop. (Ubuntu is not restricting the resources unless specified with the run command).
Should I run the project with npm or docker?
Docker is the recommended way to run the project.
License
This project is licensed under the MIT License.
For agents
This page has a .md twin and JSON over the API.