Video Editor MCP server

The Video Editor MCP server provides an interface to upload, edit, search, and generate videos through an integration with Video Jungle. It allows AI assistants like Claude to interact with your video content, enabling tasks from simple video uploads to creating automated video edits.

Installation

Prerequisites

Before installing, you need to:

1. Sign up for an account at Video Jungle
2. Obtain your API key from Video Jungle settings

Installation Options

Using Smithery

The easiest way to install Video Editor MCP for Claude Desktop is through Smithery:

npx -y @smithery/cli install video-editor-mcp --client claude

Manual Installation

To install the package manually:

pip install video-editor-mcp

Configuration for Claude Desktop

You'll need to modify your Claude Desktop configuration file:

On MacOS:

~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows:

%APPDATA%/Claude/claude_desktop_config.json

Add the following to your configuration file:

"mcpServers": {
  "video-editor-mcp": {
    "command": "uvx",
    "args": [
      "video-editor-mcp",
      "YOURAPIKEY"
    ]
  }
}

Replace YOURAPIKEY with your actual Video Jungle API key.

Enabling Local Photos Access

To enable searching your local Photos app (MacOS only):

"video-jungle-mcp": {
  "command": "uvx",
  "args": [
    "video-editor-mcp",
    "YOURAPIKEY"
  ],
  "env": {
    "LOAD_PHOTOS_DB": "1"
  }
}

Usage

Starting the Server

Run the MCP server with your API key:

uv run video-editor-mcp YOURAPIKEY

To enable Photos app search on MacOS:

LOAD_PHOTOS_DB=1 uv run video-editor-mcp YOURAPIKEY

Available Tools

Adding Videos

The add-video tool downloads and analyzes a video from a URL:

can you download the video at https://www.youtube.com/shorts/RumgYaH5XYw and name it fly traps?

This downloads the video, adds it to your library, and performs multi-modal analysis on both audio and visual content.

Searching Videos

Search your video library using the search-videos tool:

can you search my videos for fly traps?

Search results include metadata about the content and timestamps, which can be used for editing.

Searching Local Videos

To search videos in your local Photos app (requires LOAD_PHOTOS_DB=1):

can you search my local video files for Skateboard?

This will find videos in your Photos app that match the search terms using Apple's tags.

Generating Edits

Create edits based on search results with generate-edit-from-videos:

can you create an edit of all the times the video says "fly trap"?

For creating an edit from a single video, use generate-edit-from-single-video:

can you create an edit of all the times this video says the word "fly trap"?

Note that video editing tools rely on context within the current chat session.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.