Log inSubmit server
Lumiclip logo

Lumiclip

Creates scored, vertical short-form clips from YouTube videos through MCP-compatible AI assistants.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Lumiclip

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

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "lumiclip": {
      "command": "npx",
      "args": [
        "-y",
        "@lumiclip/mcp-server"
      ],
      "env": {
        "LUMICLIP_API_KEY": "YOUR_VALUE_HERE",
        "LUMICLIP_API_URL": "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.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The lumiclip MCP server turns YouTube videos into short-form clips through an MCP-compatible assistant. It submits a video for processing, detects highlights, reframes output to 9:16, adds subtitles, and provides download URLs when exports finish. Use it when an agent needs to create and monitor clips without manually calling the REST API. Processing can be tracked by polling or completed through a callback webhook.

Use cases

  • Create vertical clips from a YouTube video
  • Monitor asynchronous clip-generation projects
  • Retrieve the highest-scoring exported clip
  • Send completed clip results to a webhook
  • Check available Lumiclip credits

Key features

  • YouTube URL clip generation
  • 9:16 vertical reframing
  • Subtitle-enabled exports
  • Score-sorted clip results
  • Polling and webhook completion
  • Project and usage tracking

Tools5

What Lumiclip lets your agent do. Expand a tool for its parameters.

Self-reported~87 tokens of context

Security & health

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

ActiveLast checked 3d ago

Recent health check succeeded.

6/6 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @lumiclip/mcp-server (npm)

Adoption & maintenance

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

npm downloads166Package downloads in the last 30 days.
Last commit4mo agoMost recent push to the default branch.
Tools exposed5Callable tools this server registers over MCP.

How Lumiclip works

What the lumiclip MCP server does

The lumiclip MCP server connects an MCP client to Lumiclip’s video-processing API. It accepts a full YouTube URL, starts a clip-generation project, and returns a project ID immediately. Lumiclip processes the source video, identifies highlights, creates vertical 9:16 clips, adds subtitles, and exposes finished media through download and thumbnail URLs.

The service is suited to workflows that turn long YouTube recordings into short-form content. Optional start and end times allow a request to target only part of a video. Results include clip titles, durations, scores, explanations, export status, and available video qualities.

How it works

Call generate_clips with a YouTube URL. The response includes a project_id, current status, a polling path, and an estimated processing time. An agent can then call get_project_status every 10–15 seconds until the project completes. Completed clips are ordered by score, with the highest-scoring result first.

Instead of polling, pass a callback_url to receive a POST when processing finishes. Completion and failure events include the project ID and result details. Lumiclip retries a callback up to three times if the receiving server does not respond. Optional callback signature verification uses the X-Lumiclip-Signature header and an HMAC-SHA256 value derived from the API key.

Projects move through pending, processing, and completed states, with additional outcomes for projects that produce no clips or fail. Individual clips also have export states; their download URL becomes available after export completes.

Setup and configuration

Create an API key through Lumiclip’s developer page, then run the package with npx:

bash
LUMICLIP_API_KEY=sk_live_... npx @lumiclip/mcp-server

For Claude Desktop or Cursor, add the server command and API key to the relevant MCP configuration. The package reads LUMICLIP_API_KEY, which is required. LUMICLIP_API_URL is optional and defaults to https://api.lumiclip.ai.

A remote Streamable HTTP endpoint is available at https://mcp.lumiclip.ai/mcp. Remote requests use an Authorization: Bearer header.

Tools and capabilities

  • generate_clips: Starts processing and accepts optional segment boundaries and a callback URL.
  • get_project_status: Retrieves processing progress and completed clips.
  • list_projects: Lists projects, with status filtering and a configurable limit from 1 to 100.
  • get_clip: Returns detailed metadata and video URLs for one clip.
  • check_usage: Reports the current plan, total credits, remaining credits, and billing period.

Limitations and notes

Requests require a valid YouTube URL and an API key. Insufficient credits, invalid URLs, authentication failures, rate limits, unavailable videos, and server errors can prevent processing. A completed project may contain no clips. The lumiclip MCP server returns links to exported media; the material does not describe local file storage or editing controls beyond the documented generation options.

Read the full README View source on GitHub

Reviews

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

Frequently Asked Questions about Lumiclip

lumiclip is an MCP server that connects AI assistants to Lumiclip’s video-processing API. Its main tools start clip generation from YouTube URLs, check project status, list projects, retrieve individual clip details, and report plan usage and remaining credits.

Install it by running `npx @lumiclip/mcp-server` with `LUMICLIP_API_KEY` set. For Claude Desktop or Cursor, add the package command and key to the client’s MCP configuration.

Yes, lumiclip works with Cursor. Add an MCP server entry to `.cursor/mcp.json`, use `npx` with `@lumiclip/mcp-server`, and provide `LUMICLIP_API_KEY` in the entry’s environment settings.

It returns completed clips through `get_project_status` after processing finishes, or through a POST callback when `generate_clips` receives a `callback_url`. Results include scored clips and download URLs when their exports are complete.

It requires `LUMICLIP_API_KEY`. `LUMICLIP_API_URL` is optional and defaults to `https://api.lumiclip.ai`, so it is not needed for the standard configuration.

Related MCP servers

All in Multimedia Process All alternatives
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 PreviewLumiclip AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/lumiclip?style=directory)](https://allmcps.com/mcp/lumiclip)
HTML Embed
<a href="https://allmcps.com/mcp/lumiclip"><img src="https://allmcps.com/api/badge/lumiclip?style=directory" alt="Lumiclip on AllMCPs" /></a>