submagic-mcp-server
Connects AI assistants to Submagic's video editing API for creating viral short-form content with AI captions in 107 languages.
README
Submagic MCP Server
mcp-name: io.github.sidart10/submagic-mcp-server
Connect your AI assistant to Submagic's powerful video editing API. Create viral short-form content, add AI captions in 107 languages, and automate your video production workflow directly from Claude or any MCP-compliant client.
Table of Contents
Features
- Global Reach: Automatic AI captions with 98%+ accuracy in 107 languages.
- Dynamic Editing: Magic zooms and auto-inserted B-rolls with configurable coverage.
- Smart Cleanup: Automated silence removal (3 speeds) and filler word removal ("um", "uh").
- Content Repurposing: Convert YouTube videos into viral short-form clips (TikTok, Reels, Shorts).
- Professional Styling: Access 30+ trending templates (Hormozi, Beast, Sara).
- Optimized Exports: Ready-to-post formats for all major platforms (9:16, 1:1, 16:9, 4:5).
Getting Started
Prerequisites
- Python 3.10 or higher
- A Submagic API Key (Get one at Submagic.co)
Installation
Option 1: Install via PyPI (Recommended)
pip install submagic-mcp-server
Option 2: Install from Source
git clone https://github.com/sidart10/submagic-mcp-server.git
cd submagic-mcp-server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
Configuration
-
Get your API Key: Sign up at submagic.co to retrieve your API key.
-
Configure Claude Desktop: Add the server definition to your
claude_desktop_config.jsonfile.If installed via PyPI:
{ "mcpServers": { "submagic": { "command": "python", "args": ["-m", "submagic_mcp"], "env": { "SUBMAGIC_API_KEY": "sk-your-api-key-here" } } } }If installed from source (use absolute paths):
{ "mcpServers": { "submagic": { "command": "/absolute/path/to/venv/bin/python", "args": ["/absolute/path/to/submagic_mcp.py"], "env": { "SUBMAGIC_API_KEY": "sk-your-api-key-here" } } } } -
Restart Claude Desktop: Relaunch the application to load the new server.
Usage Examples
Here are common workflows you can automate:
Create Video with AI Captions
Upload a raw video and apply professional styling with captions.
submagic_create_project(
title="Product Demo Launch",
language="en",
video_url="https://example.com/raw-video.mp4",
template_name="Hormozi 2",
remove_silence_pace="fast",
magic_zooms=True
)
Generate TikTok Clips from YouTube
Turn a long-form YouTube video into multiple engaging shorts.
submagic_create_magic_clips(
title="Podcast Highlights",
youtube_url="https://youtube.com/watch?v=your-video-id",
language="en",
min_clip_length=30,
max_clip_length=60
)
Export for Social Media
Finalize and export your project in the perfect format for Instagram Reels.
submagic_export_project(
project_id="your-project-uuid",
width=1080,
height=1920,
fps=30
)
Available Tools
| Tool | Description | Rate Limit |
|---|---|---|
submagic_list_languages |
Get list of supported languages (107+) | 1000/hr |
submagic_list_templates |
Get available video styling templates | 1000/hr |
submagic_create_project |
Create a new video project with AI features | 500/hr |
submagic_get_project |
Get project details, status, and download URL | 500/hr |
submagic_update_project |
Update settings (silence, b-rolls) after creation | 100/hr |
submagic_export_project |
Render and export the final video | 500/hr |
submagic_create_magic_clips |
Generate shorts from YouTube videos | 500/hr |
Limitations
- Input: Videos must be publicly accessible URLs.
- Size: Maximum file size is 2GB.
- Duration: Maximum video duration is 2 hours.
- Formats: Supports MP4 and MOV.
- Performance:
remove_bad_takesadds 1-2 minutes to processing time. - API Coverage: Some dashboard features are not yet available via API. See
docs/API_LIMITATIONS_DISCOVERED.mdfor details.
Contributing
We welcome contributions! Please follow these steps:
- Fork the repository.
- Create a feature branch:
git checkout -b feature/new-tool. - Install development dependencies:
pip install -r requirements.txt. - Run tests to ensure everything works:
python -m pytest tests/. - Submit a Pull Request describing your changes.
See docs/development-guide.md for more detailed instructions.
License
MIT License. See LICENSE for details.
Resources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.