video-edit-tools
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@video-edit-toolstrim first 10 seconds and add title 'Demo'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
video-edit-tools
Deterministic video editing SDK for AI agents. Ships with MCP tools.
Demo
Related MCP server: mcp-ffmpeg
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-toolsQuick 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.
This server cannot be deployed
Maintenance
Related MCP Connectors
Video, audio, and image processing for AI agents: convert, transcribe, upscale - 150+ operations.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Build, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.
FFmpeg as a service for AI agents: typed video editing tools, async jobs, downloadable outputs.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP tools for video transcoding, document conversion, and multi-step pipelines — callable by any AI agent.12429 npm1MIT
- AlicenseAqualityCmaintenanceProvides 30+ FFmpeg video and audio editing tools via MCP, enabling AI assistants to perform operations like trimming, transcoding, overlays, and composition directly.274MIT
- FlicenseNot gradedqualityDmaintenanceEnables agentic video editing and composition via MCP, allowing creation and manipulation of multi-track timelines with clips, transitions, filters, and text overlays, then rendering to MP4 using the melt-7 CLI.-
- AlicenseNot gradedqualityBmaintenanceMCP server for OmniCut that provides 29 deterministic video editing tools (trim, transition, render, etc.) for AI agents to drive the video editor end-to-end.6 npm1ISC