video-edit-tools
Enables AI agents to perform deterministic video editing operations like trim, resize, add text, and more using MCP tools.
README
video-edit-tools
Deterministic video editing SDK for AI agents. Ships with MCP tools.
Demo
<p align="center" width="100%"> <video src="https://github.com/user-attachments/assets/a1e5855c-b622-4ac0-9529-c2d9c26658f4" width="80%" controls></video> </p>
Features
- Never Throws: All functions return
Promise<Result<T>>. - Deterministic: Same input + same options = same output.
- Pure Functions: No side effects, no global state.
- TypeScript First: Strict types, comprehensive JSDoc.
- Zero Python: Uses
@ffmpeg-installer/ffmpegand@xenova/transformers. No system dependencies needed.
Installation
npm install video-edit-tools
Quick Start
import { pipeline, getMetadata } from 'video-edit-tools';
const result = await pipeline('input.mp4', [
{ op: 'trim', start: 0, end: 10 },
{ op: 'resize', width: 1280, height: 720, fit: 'cover' },
{ op: 'addText', layers: [{ text: 'Hello', x: 100, y: 100, fontSize: 48, color: '#FFFFFF' }] }
]);
if (result.ok) {
const meta = await getMetadata(result.data);
console.log(meta);
// Do something with result.data (Buffer)
} else {
console.error(result.error);
}
MCP Server Setup
Add this configuration to your Claude Desktop or Cursor MCP settings to enable the agent tools:
{
"mcpServers": {
"video-edit-tools": {
"command": "node",
"args": ["/absolute/path/to/node_modules/video-edit-tools/dist/mcp/index.js"]
}
}
}
Or using npx if installed globally/locally:
{
"mcpServers": {
"video-edit-tools": {
"command": "npx",
"args": ["video-edit-tools-mcp"]
}
}
}
Available Operations
trim,concat,resize,crop,changeSpeed,convert,extractFramesaddText,addSubtitles,composite,gradientOverlay,blurRegion,addTransitionextractAudio,replaceAudio,adjustVolume,muteSection,transcribe(Whisper)adjust,applyFilter,detectScenes,generateThumbnailpipeline(sequential),batch(parallel pipelines)
Architecture
This package wrappers fluent-ffmpeg and @ffmpeg-installer/ffmpeg to safely run operations locally without needing system paths. Temporary files are safely managed in the OS temp directory and cleaned up via process.on('exit') hooks.
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.