Back to MCP Catalog

Video Jungle MCP Server

Art & CulturePython
Upload, edit, search, and generate videos with AI assistance
Available Tools

add-video

Add a video from a URL to your Video Jungle library

urlname

search-videos

Search videos in your library using embeddings and keywords

query

search-local-videos

Search videos in your local Photos app (MacOS only, requires LOAD_PHOTOS_DB=1)

query

generate-edit-from-videos

Generate a rendered video edit from a set of video files

videosinstructions

generate-edit-from-single-video

Generate an edit from a single input video file

videoinstructions

Video Jungle provides a powerful interface for video editing and management through Claude. It allows you to upload videos from URLs, search through your video library using natural language, and automatically generate edits based on content analysis. The MCP leverages multimodal analysis to understand both audio and visual components, making it possible to search for specific moments or create targeted edits from your video collection.

Video Jungle

Video Jungle is a powerful MCP that enables Claude to help you manage, search, and edit videos. With multimodal analysis capabilities, it understands both audio and visual content in your videos, allowing for sophisticated search and editing operations.

Prerequisites

Before using Video Jungle, you'll need to:

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

Installation

For Claude Desktop

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

  • MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json

Add the following to your configuration:

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

Replace YOUR_API_KEY with your actual Video Jungle API key.

For Development/Local Setup

If you're working with a local copy of the repository:

"mcpServers": {
  "video-editor-mcp": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/video-editor-mcp",
      "run",
      "video-editor-mcp",
      "YOUR_API_KEY"
    ]
  }
}

Enabling Local Photos App Access (MacOS only)

To allow searching through your local Photos app:

"video-jungle-mcp": {
  "command": "uv",
  "args": [
    "--directory",
    "/path/to/video-editor-mcp",
    "run",
    "video-editor-mcp",
    "YOUR_API_KEY"
  ],
  "env": {
    "LOAD_PHOTOS_DB": "1"
  }
}

Using Video Jungle

Once installed, you can interact with Video Jungle through Claude using natural language. Here are some examples:

  1. Adding videos to your library:

    • "Can you download the video at https://example.com/video.mp4 and name it 'My Video'?"
  2. Searching your video library:

    • "Can you search my videos for skateboarding tricks?"
    • "Find videos that mention climate change"
  3. Searching local videos (if enabled):

    • "Can you search my local video files for birthday parties?"
  4. Creating video edits:

    • "Create an edit of all the times someone mentions 'artificial intelligence' in these videos"
    • "Make a compilation of the sunset scenes from my beach videos"
  5. Editing a single video:

    • "Can you create an edit of all the times this video shows a dog running?"

The MCP will handle the processing and return results or edits based on your requests.

Resource Management

Video Jungle uses a custom vj:// URI scheme to reference videos and projects in your library. These URIs will be returned when you add videos or create edits, and can be used in subsequent operations.

Troubleshooting

If you encounter issues:

  1. Check that your API key is correctly configured
  2. Ensure the MCP server is running (restart Claude if necessary)
  3. For development, check the app.log file in the project directory for detailed logs

For the best debugging experience, use the MCP Inspector:

npx @modelcontextprotocol/inspector uv run --directory /path/to/video-editor-mcp video-editor-mcp YOUR_API_KEY

Related MCPs

Rijksmuseum
Art & CultureTypeScript

Access and explore the Rijksmuseum's art collection through natural language

AniList
Art & CultureTypeScript

Access and interact with anime, manga, character, and user data from AniList

Giphy
Art & CultureTypeScript

Access and search for GIFs from Giphy's vast library

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.