Skip to content
MCP server

Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1)

MCP server that lets AI agents turn raw footage into captioned, reframed short-form video

Install
Pricing
Freemium
Platforms
API, CLI, Web
Runs
Remotely
Version
0.7.0
Listing updated
today

Similar MCP servers

About Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1)

Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) is a freemium MCP server for video editing. It runs as a hosted remote server, so there is nothing to install locally.

The README describes Levea as an MCP client that sends a plain-language video request from a local agent such as Claude, Cursor or Cline to a cloud GPU editing backend. The agent plans the edit, runs it and exports an MP4, with a verification pass on rendered frames before results are reported.

Beyond short-form basics like 9:16 reframing, auto-captions and silence removal, the server exposes a larger toolset: 280+ caption templates, chroma key and AI background removal, multicam podcast sync, voiceover and dubbing, and a library of licensed music and sound effects. Users can pass a brief in one sentence or a multi-step creative brief, and can require plan approval before anything runs.

The README labels the project beta and warns that the agent can make mistakes, so previewing outputs before publishing is advised. It is aimed at creators, podcasters, marketers and educators who want to produce clips from long recordings without working in a timeline editor.

Install

Run in a terminal

claude mcp add --transport http video-editor-broll-reframe-chromakey-voiceover-color-vfx https://api.livecore.ai/api/v1/misc/mcp

Add to Settings → Connectors → Add custom connector

https://api.livecore.ai/api/v1/misc/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "video-editor-broll-reframe-chromakey-voiceover-color-vfx": {
      "url": "https://api.livecore.ai/api/v1/misc/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "video-editor-broll-reframe-chromakey-voiceover-color-vfx": {
      "type": "http",
      "url": "https://api.livecore.ai/api/v1/misc/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "video-editor-broll-reframe-chromakey-voiceover-color-vfx": {
      "serverUrl": "https://api.livecore.ai/api/v1/misc/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://api.livecore.ai/api/v1/misc/mcp

Enter a Name (for example "Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1)"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "video-editor-broll-reframe-chromakey-voiceover-color-vfx": {
      "type": "http",
      "url": "https://api.livecore.ai/api/v1/misc/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (12)

Taken from the project documentation; the running server may differ.

autonomous_edit
Runs a natural-language video edit that the agent plans, executes, verifies and exports.
autonomous_edit_streaming
Same as autonomous_edit with per-step progress over server-sent events.
queue_edit
Starts an asynchronous edit without waiting for the result.
search_tools
Finds available canonical editing actions.
execute_action
Runs a single canonical editing action on the project.
execute_batch
Runs several canonical editing actions in one call.
render_preview
Returns GPU-composited JPEG screenshots of the current scene.
list_caption_templates
Lists built-in and saved caption template ids.
apply_caption_template
Applies a caption template to a project.
check_job_status
Polls an asynchronous job.
check_task_status
Polls an asynchronous task.
get_active_task
Returns the in-flight task for a project.

What it does

Natural language edit requests
A single prompt can describe trims, grades, captions and exports, and the agent plans the sequence of steps.
Short-form reframing
Converts landscape footage to vertical 9:16 with face tracking and caption-safe framing.
Caption template library
Offers 280+ built-in animated caption styles plus support for saving custom templates.
Plan approval mode
Can pause after planning so a user reviews the proposed edit before rendering begins.
Background and green screen compositing
Supports chroma key and AI alpha-matte background removal with a new background composited behind the subject.
Remote and local MCP access
Runs as a local npm package via stdio or as a hosted Streamable HTTP endpoint with OAuth 2.1.

Good for

  • Cutting several vertical clips with captions from a long podcast or webinar recording
  • Reframing a landscape video for TikTok, Reels and YouTube Shorts in one pass
  • Removing silences and filler words from a talking-head recording
  • Replacing a green screen background in a short clip from a chat assistant
  • Adding a cloned-voice narration or translated dub to an existing video

Pricing

Freemium

Free tier with 3 cloud edits/month and watermark; paid plans on livecore.ai (prices not stated in the content).

Prices change. Check livecore.ai before you buy.

Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) FAQ

How do I connect it to an MCP client?

The README gives an npx config using levea-mcp-server with LEVEA_API_URL and LEVEA_API_KEY, and a hosted endpoint at https://api.livecore.ai/api/v1/misc/mcp that supports OAuth 2.1 without an API key.

Is there a free tier?

The README says a free tier exists with 3 cloud edits per month, 720p export and a watermark, with paid plans available on livecore.ai.

How long does an edit take?

According to the README, a simple edit with export takes a few minutes, while a full edit with motion graphics, music and export can take 10 to 20 minutes.

What license is the MCP server under?

The README states the license is MIT.

Does the agent ask for approval before editing?

Passing requirePlanApproval set to true makes the agent stop after planning and wait for approval before running the edit.

Is Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) free?

Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) has a free plan, with paid plans for more usage or features.

How do I add Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) to Claude Code?

Run this command in your terminal: claude mcp add --transport http video-editor-broll-reframe-chromakey-voiceover-color-vfx https://api.livecore.ai/api/v1/misc/mcp

What are the best alternatives to Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1)?

The closest alternatives to Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) are Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1), Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1), Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1), Levea — Autonomous AI Video Editor (37 Tools, 280+ Caption Templates, OAuth 2.1) and Levea — Autonomous AI Video Editor (Captions, Shorts, TikTok, Reels, Podcast, VFX).

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers