Video Editing MCP logo

Video Editing MCP

by burningion

Connects AI agents to Video Jungle for video analysis, search, edit generation, and local editing workflows.

Install Video Editing MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "burningion-video-editing-mcp": {
      "command": "uvx",
      "args": [
        "video-editor-mcp"
      ],
      "env": {
        "LOAD_PHOTOS_DB": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx video-editor-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 24d ago.

Overview

burningion/video-editing-mcp MCP server connects an MCP client to Video Jungle for uploading, analyzing, searching, and generating video edits. It exposes tools for managing projects, finding moments with embeddings and keywords, creating edits from one or multiple videos, and updating edits. A local-editing tool creates an OpenTimelineIO project and downloads it for DaVinci Resolve Studio, which must already be running. Use it when an agent needs to turn analyzed video collections or selected footage into editable video projects.

Use cases

  • Import and analyze videos from URLs
  • Search a video collection for spoken or visual moments
  • Generate edits from one or multiple videos
  • Prepare OpenTimelineIO projects for DaVinci Resolve Studio
  • Search tagged videos in the macOS Photos app

Key features

  • Video URL import and multimodal analysis
  • Embedding and keyword video search
  • Single-video and multi-video edit generation
  • Video Jungle project and asset management
  • OpenTimelineIO export for local editing
  • Optional macOS Photos search

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

9/9 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 11d ago via OSV.dev · video-editor-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars295Stargazers on the source repository.
Last commit1y agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity5 viewsConfig copies, upvotes, and views on AllMCPs.

How Video Editing MCP works

What burningion/video-editing-mcp does

burningion/video-editing-mcp connects an MCP client with Video Jungle, a service for storing and analyzing video assets and generating edits. It supports adding a video from a URL, creating projects, inspecting project assets, searching indexed footage, and producing edits from either one video or a group of videos.

Video analysis covers both visual and audio content. Search results include information about what appears or is said in a video and when it occurs, giving later edit-generation requests temporal context. The server also provides an update operation for changing edit information while Video Jungle is open.

The repository is categorized under the 🎥 Multimedia Process category. It is a fit for conversational workflows that start with a video URL or an existing Video Jungle collection and end with a rendered edit or a project prepared for local editing.

How it works

The add-video tool accepts a URL, downloads the source, adds it to the library, analyzes it, and returns a vj:// URI. Projects and individual videos are exposed through the custom vj:// URI scheme. Project resources include a name and description.

Use search-videos with keywords or concepts to retrieve relevant footage. The server uses embeddings and keywords, and the returned metadata can guide a subsequent request such as selecting every occurrence of a phrase. generate-edit-from-videos creates a rendered edit from multiple video files, while generate-edit-from-single-video creates an edit from one existing file. The current edit-generation workflow depends on information available in the active chat.

edit-locally creates an OpenTimelineIO project and downloads it to the local machine for opening in DaVinci Resolve Studio. Resolve Studio must be running before this tool is called. A separate local search workflow can query videos in the macOS Photos app using Apple tags.

Setup and configuration

A Video Jungle account and API key are required. Obtain the key from the Video Jungle profile settings, then start the server with uv run video-editor-mcp YOURAPIKEY. The published Claude Desktop configuration uses uvx with the package name and API key as an argument. The repository also documents a local-development configuration using uv --directory.

Set LOAD_PHOTOS_DB=1 when local Photos app video search is needed. This option is intended for macOS and allows searches over videos in the Photos database. For example:

bash
LOAD_PHOTOS_DB=1 uv run video-editor-mcp YOURAPIKEY

The server communicates over stdio. Logs are written to app.log, which can be followed from the project directory.

Tools and capabilities

  • add-video: imports and analyzes a video from a URL.
  • create-videojungle-project: creates a project for scripts, analyzed videos, and images used in edit generation.
  • search-videos: searches analyzed videos using embeddings and keywords.
  • search-local-videos: searches local Photos app videos when enabled.
  • get-project-assets: retrieves assets from a project.
  • generate-edit-from-videos: renders an edit from multiple video files.
  • generate-edit-from-single-video: creates an edit from one video.
  • edit-locally: downloads an OpenTimelineIO project for DaVinci Resolve Studio.
  • update-video-edit: updates edit information while Video Jungle is open.

Limitations and notes

burningion/video-editing-mcp requires a Video Jungle account and API key; the key is passed when launching the process rather than documented as an environment variable. Local Photos searching requires LOAD_PHOTOS_DB=1 and is described for macOS. Local editing depends on DaVinci Resolve Studio already running. Prompts are listed as coming soon, and edit generation currently relies on the active chat context.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Video Editing MCP

burningion/video-editing-mcp is an MCP server that connects AI clients to Video Jungle for video storage and analysis. Its main tools add videos from URLs, search analyzed footage, create projects, generate edits from one or multiple videos, update edits, and export local OpenTimelineIO projects for DaVinci Resolve Studio.

Install it with `uv` or `uvx`, then provide your Video Jungle API key when starting the process. For Claude Desktop, the documented published configuration uses `uvx` with `video-editor-mcp` and the key as an argument. Smithery also provides a Claude Desktop installation command.

Yes, burningion/video-editing-mcp works with Claude Desktop through a stdio configuration.

Set `LOAD_PHOTOS_DB=1` before starting the server, then use the local video search workflow. This capability is documented for macOS and searches videos in the Photos app using Apple tags, allowing an MCP client to find local footage such as videos tagged with a subject.

Yes, its `edit-locally` tool creates an OpenTimelineIO project and downloads it to the machine for opening in DaVinci Resolve Studio. Resolve Studio must already be running before the tool is called.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewVideo Editing MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/burningion-video-editing-mcp?style=directory)](https://allmcps.com/mcp/burningion-video-editing-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/burningion-video-editing-mcp"><img src="https://allmcps.com/api/badge/burningion-video-editing-mcp?style=directory" alt="Video Editing MCP on AllMCPs" /></a>