Short Video Maker MCP server

Automates short-form video creation by combining text-to-speech, captions, background videos, and music for platforms like TikTok, Instagram Reels, and YouTube Shorts.
Back to servers
Setup instructions
Provider
David Gyori
Release date
Apr 15, 2025
Language
TypeScript
Package
Stats
2.5K downloads
525 stars

The MCP Server provides a robust solution for generating short-form videos by combining text-to-speech, automatic captions, background videos, and music. This tool allows you to create engaging content without requiring heavy GPU resources or expensive third-party APIs.

Installation

Docker Installation (Recommended)

Three Docker images are available to suit different use cases:

Tiny (Best for Limited Resources)

docker run -it --rm --name short-video-maker -p 3123:3123 -e LOG_LEVEL=debug -e PEXELS_API_KEY=your_key_here gyoridavid/short-video-maker:latest-tiny

Normal

docker run -it --rm --name short-video-maker -p 3123:3123 -e LOG_LEVEL=debug -e PEXELS_API_KEY=your_key_here gyoridavid/short-video-maker:latest

CUDA (For Nvidia GPU Users)

docker run -it --rm --name short-video-maker -p 3123:3123 -e LOG_LEVEL=debug -e PEXELS_API_KEY=your_key_here --gpus=all gyoridavid/short-video-maker:latest-cuda

Using Docker Compose

version: "3"

services:
  short-video-maker:
    image: gyoridavid/short-video-maker:latest-tiny
    environment:
      - LOG_LEVEL=debug
      - PEXELS_API_KEY=your_key_here
    ports:
      - "3123:3123"
    volumes:
      - ./videos:/app/data/videos # expose the generated videos

NPM Installation

While Docker is recommended, you can run with npm on supported platforms:

  • Ubuntu ≥ 22.04 (with required packages)
  • Mac OS (with ffmpeg installed via Homebrew)

Note: Windows is not currently supported.

Requirements

  • Internet connection
  • Free Pexels API key
  • ≥ 3 GB free RAM (4GB recommended)
  • ≥ 2 vCPU
  • ≥ 5GB disk space

Using the Web UI

A user-friendly web interface is available at http://localhost:3123 for generating videos through your browser.

Configuration Options

Environment Variables

Basic Configuration:

Variable Description Default
PEXELS_API_KEY Your free Pexels API key
LOG_LEVEL Pino log level info
WHISPER_VERBOSE Whether to forward whisper.cpp output false
PORT Server listening port 3123

System Configuration:

Variable Description Default
KOKORO_MODEL_PRECISION Model size (fp32, fp16, q8, q4, q4f16) Varies by image
CONCURRENCY Number of parallel browser tabs for rendering Varies by image
VIDEO_CACHE_SIZE_IN_BYTES Cache size for video frames Varies by image

Video Generation Options

Option Description Default
paddingBack End screen duration after narration (ms) 0
music Background music mood random
captionPosition Caption position (top, center, bottom) bottom
captionBackgroundColor Active caption background color blue
voice Kokoro voice to use af_heart
orientation Video orientation (portrait/landscape) portrait
musicVolume Background music volume (low/medium/high/muted) high

API Usage

MCP Server Endpoints

  • /mcp/sse
  • /mcp/messages

Available MCP Tools

  • create-short-video: Creates a short video with AI-determined configuration
  • get-video-status: Checks video generation status

REST API Endpoints

Create a Short Video

curl --location 'localhost:3123/api/short-video' \
--header 'Content-Type: application/json' \
--data '{
    "scenes": [
      {
        "text": "Hello world!",
        "searchTerms": ["river"]
      }
    ],
    "config": {
      "paddingBack": 1500,
      "music": "chill"
    }
}'

Check Video Status

curl --location 'localhost:3123/api/short-video/{id}/status'

Get Generated Video

curl --location 'localhost:3123/api/short-video/{id}'

List All Videos

curl --location 'localhost:3123/api/short-videos'

Delete a Video

curl --location --request DELETE 'localhost:3123/api/short-video/{id}'

Get Available Voices

curl --location 'localhost:3123/api/voices'

Get Available Music Tags

curl --location 'localhost:3123/api/music-tags'

Troubleshooting

Docker Issues

  • Ensure Docker has at least 3GB of free memory allocated
  • If using WSL2 on Windows, set resource limits with the wsl utility

n8n Integration

When connecting with n8n, use the appropriate URL based on your setup:

  • Local n8n + local Docker: http://localhost:3123 or service name
  • Local n8n + local npm: http://localhost:3123
  • Docker n8n + local npm: http://host.docker.internal:3123
  • Cloud deployments: Use your IP address http://{YOUR_IP}:3123

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "short-video-maker" '{"command":"npx","args":["-y","short-video-maker"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "short-video-maker": {
            "command": "npx",
            "args": [
                "-y",
                "short-video-maker"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "short-video-maker": {
            "command": "npx",
            "args": [
                "-y",
                "short-video-maker"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later