mcp-lumiclip
OfficialThe mcp-lumiclip server lets you automatically turn YouTube videos into short, vertical (9:16), subtitled clips using AI — accessible from Claude, Cursor, or any MCP-compatible AI assistant.
Generate Clips: Start AI-powered clip generation from a YouTube URL. Optionally specify a time range (
start_time/end_time) to process only a segment, or provide acallback_urlwebhook instead of polling. Returns aproject_idimmediately.Check Project Status: Poll a job using its
project_id. Returns progress and — when complete — clips sorted by AI score, each with a download URL, title, duration, thumbnail, and quality info.List Projects: Retrieve a paginated list of your projects with optional filtering by status (
pending,processing,completed,failed, etc.).Get Clip Details: Fetch full details for a single clip, including multiple resolution download URLs (720p/1080p), thumbnail, score, and the AI-generated reason for selecting that clip.
Check Usage: View your current plan, remaining credits, and billing period — useful to confirm capacity before starting a new job.
@lumiclip/mcp-server
Turn long videos into short clips — from Claude, Cursor, or any AI assistant that supports MCP.
Give it a YouTube link. It finds the best moments, reframes for vertical video (9:16), adds subtitles, and returns download-ready clips.
Quick Start
Get an API key at app.lumiclip.ai/developers
Run:
LUMICLIP_API_KEY=sk_live_... npx @lumiclip/mcp-serverRelated MCP server: Image Metadata AI MCP
Setup
Claude Desktop / Cursor
Add to your config file — claude_desktop_config.json for Claude, .cursor/mcp.json for Cursor:
{
"mcpServers": {
"lumiclip": {
"command": "npx",
"args": ["@lumiclip/mcp-server"],
"env": {
"LUMICLIP_API_KEY": "sk_live_..."
}
}
}
}Cursor Directory
Smithery
npx @smithery/cli mcp add lumiclip/lumiclipRemote (Streamable HTTP)
For n8n, custom integrations, or any client that supports remote MCP:
Endpoint:
https://mcp.lumiclip.ai/mcpAuth:
Authorization: Bearer sk_live_...Transport: Streamable HTTP (POST)
Tools
Tool | What it does |
| Start clip generation from a YouTube URL. Returns a |
| Check progress and get clips when ready. Clips are sorted by score (best first). |
| List your projects with status and clip counts. |
| Get full details for a single clip. |
| See your plan, remaining credits, and usage. |
How It Works
Call
generate_clipswith a YouTube URLGet back a
project_idimmediatelyPoll
get_project_statusevery 10–15 seconds (or pass acallback_urlfor webhook)When done, clips are sorted by score (best first), each with a
download_url
Statuses
Project: pending → processing → completed (or completed_no_clips / failed)
Processing steps: queued → DOWNLOADING_VIDEO → EXTRACTING_AUDIO → TRANSCRIBING → DETECTING_HIGHLIGHTS → CUTTING_CLIPS → EXPORTING_CLIPS → done
Clips: pending → exporting → completed (or failed). The download_url is available when clip_status is completed.
API Reference
generate_clips
Start clip generation from a YouTube video.
Field | Type | Required | Description |
| string | Yes | Full YouTube video URL |
| number | No | Start time in seconds (to process only a segment) |
| number | No | End time in seconds (to process only a segment) |
| string | No | Webhook URL to receive results when done |
{
"project_id": "43dbe622-8ac6-4579-9625-0ad7f0f9db0b",
"status": "processing",
"poll_url": "/api/v1/projects/43dbe622-8ac6-4579-9625-0ad7f0f9db0b",
"estimated_minutes": 5,
"message": "Processing started. Poll with get_project_status every 10-15 seconds until status is 'completed'."
}get_project_status
Check progress and get clips.
Field | Type | Required | Description |
| string | Yes | The project ID from |
{
"id": "43dbe622-...",
"name": "Video Title",
"status": "completed",
"step": "done",
"error": null,
"expected_clips": 9,
"duration": 639,
"created_at": "2026-03-15T02:21:46.226Z",
"clips": [
{
"id": "32538b9c-...",
"title": "One Dating Theory Leads to Chaos",
"duration": 41.83,
"score": 90,
"reason": "Sharp universal joke that hooks instantly with strong reactions.",
"clip_status": "completed",
"download_url": "https://cdn.lumiclip.ai/exports/premium/.../clip-32538b9c-....mp4",
"quality": "1080p",
"thumbnail_url": "https://cdn.lumiclip.ai/exports/premium/.../clip-32538b9c-...-thumb.jpg",
"created_at": "2026-03-15T02:29:10.954Z",
"updated_at": "2026-03-15T02:30:43.907Z"
}
]
}Clips are sorted by score (highest first).
list_projects
Field | Type | Required | Description |
| number | No | Max projects to return. Default 20, max 100. |
| string | No | Filter: |
{
"projects": [
{
"id": "43dbe622-...",
"name": "Video Title",
"status": "completed",
"step": "done",
"expected_clips": 9,
"clips_count": 8,
"duration": 639,
"created_at": "2026-03-15T02:21:46.226Z"
}
],
"total": 1,
"limit": 20,
"offset": 0
}get_clip
Field | Type | Required | Description |
| string | Yes | The clip ID from a project's clips array |
{
"id": "32538b9c-...",
"project_id": "43dbe622-...",
"title": "One Dating Theory Leads to Chaos",
"duration": 41.83,
"score": 90,
"reason": "Sharp universal joke that hooks instantly.",
"export_status": "completed",
"export_quality": "1080p",
"is_exported": true,
"video_url": "https://cdn.lumiclip.ai/...",
"video_url_720p": "https://cdn.lumiclip.ai/...",
"video_url_1080p": "https://cdn.lumiclip.ai/...",
"thumbnail_url": "https://cdn.lumiclip.ai/...",
"created_at": "2026-03-15T02:29:10.954Z",
"updated_at": "2026-03-15T02:30:43.907Z"
}check_usage
No input required.
{
"plan": "pro",
"credits_remaining": 450,
"credits_total": 500,
"period_start": "2026-03-01T00:00:00.000Z",
"period_end": "2026-04-01T00:00:00.000Z"
}Errors
HTTP Status | Error | What to do |
400 | Invalid YouTube URL | Check the URL format |
401 | Unauthorized | Check your API key |
402 | Insufficient credits | Buy more credits or use a shorter video |
429 | Rate limit exceeded | Wait and try again |
500 | Internal server error | Try again later |
Webhooks
Pass a callback_url when calling generate_clips to receive a POST when all clips are ready.
Completed:
{
"event": "project.completed",
"project_id": "43dbe622-...",
"status": "completed",
"source_url": "https://www.youtube.com/watch?v=H51iLa1leOU",
"clips": [
{
"id": "32538b9c-...",
"title": "One Dating Theory Leads to Chaos",
"duration": 41.83,
"score": 90,
"download_url": "https://cdn.lumiclip.ai/exports/premium/.../clip-32538b9c-....mp4",
"thumbnail_url": "https://cdn.lumiclip.ai/exports/premium/.../clip-32538b9c-...-thumb.jpg",
"quality": "1080p"
}
]
}Failed:
{
"event": "project.failed",
"project_id": "43dbe622-...",
"status": "failed",
"error": "YouTube video is unavailable",
"clips": []
}Clips are sorted by score (highest first). We retry up to 3 times if your server doesn't respond.
Signature verification (optional): Each callback includes an X-Lumiclip-Signature header. Compute HMAC-SHA256 of the request body using SHA-256(your_api_key) as the signing key. Compare with the header value (sha256=<hex>).
Using with n8n
Option A — Webhook (recommended):
Create a workflow with a Webhook trigger node. Copy its URL.
Add an HTTP Request node:
POST https://api.lumiclip.ai/api/v1/clips/generatewith Header Auth (Authorization: Bearer sk_live_...) and body:{ "url": "https://www.youtube.com/watch?v=...", "callback_url": "https://your-n8n.com/webhook/abc123" }When clips are ready, the Webhook node receives the payload.
Best clip:
{{ $json.clips[0].download_url }}
Option B — Polling loop:
POSTto generate clips (same as above, withoutcallback_url).Wait 15 seconds → GET
https://api.lumiclip.ai/api/v1/projects/{{ $json.project_id }}→ IF status is notcompleted, loop back to Wait.
REST API
For direct HTTP calls without MCP:
Method | Endpoint | Description |
|
| Start clip generation |
|
| Get project status and clips |
|
| List projects |
|
| Get single clip details |
|
| Check credits and plan |
Base URL: https://api.lumiclip.ai — All endpoints require Authorization: Bearer sk_live_...
Environment Variables
Variable | Required | Default |
| Yes | — |
| No |
|
Links
Website: lumiclip.ai
API key: app.lumiclip.ai/developers
Pricing: lumiclip.ai/pricing
License
MIT
Available Tools
5 toolscheck_usageARead-onlyIdempotent
Returns a JSON object with plan (string), credits_remaining (number), credits_total (number), period_start (ISO date), and period_end (ISO date). Call this before generate_clips to confirm the user has enough credits.
Inputs: no named parameters.
generate_clipsA
Start AI clip generation from a YouTube video. Returns a JSON object with project_id (string), status ('processing'), poll_url (string), and estimated_minutes (number). Processing is async -- use get_project_status to poll every 10-15 seconds, or provide a callback_url to receive a webhook POST when all clips are exported with download URLs.
Inputs: url (required), start_time, end_time, callback_url.
get_clipARead-onlyIdempotent
Returns a JSON object with full clip details: id, project_id, title, duration, score, reason, export_status, export_quality (720p/1080p), is_exported, video_url, video_url_720p, video_url_1080p, thumbnail_url, created_at, updated_at.
Inputs: clip_id (required).
get_project_statusARead-onlyIdempotent
Returns a JSON object with id, name, status (pending/processing/completed/completed_no_clips/failed), step, error, expected_clips, duration, created_at, and a clips array. Clips are sorted by score (highest first). Each clip has: id, title, duration, score, reason, clip_status (pending/exporting/completed/failed), download_url (string or null), quality, thumbnail_url, created_at, updated_at. The download_url is only available when clip_status is 'completed'. Poll every 10-15 seconds until project status is 'completed'.
Inputs: project_id (required).
list_projectsARead-onlyIdempotent
Returns a JSON object with projects (array), total, limit, and offset. Each project has: id, name, status, step, expected_clips, clips_count, duration, created_at. Use the status filter to find only completed or failed projects.
Inputs: limit, status.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct purpose: check_usage for credits, generate_clips for initiating generation, get_clip for retrieving a specific clip, get_project_status for polling progress, and list_projects for enumerating projects. No functional overlap.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., generate_clips, get_project_status), making them predictable and intuitive.
Five tools is well-scoped for the server's purpose: credit checking, generation initiation, status polling, single clip retrieval, and project listing. Each tool serves a necessary function without excess.
Core workflow (check credits, generate, poll results, retrieve clips) is covered. Minor gaps like missing cancel operation or webhook management are present but not critical for basic usage.
Maintenance
Related MCP Connectors
MCP server for Wan AI video generation
MCP server for Kling AI video generation
MCP server for Google Veo AI video generation
AI video clipping MCP: long videos and podcasts into scored, captioned 9:16 shorts.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAI Ops - MCP server providing AI-powered tools and automation by MEOK AI Labs6 npm90 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceImage Metadata AI - MCP server providing AI-powered tools and automation by MEOK AI Labs4 npm32 PyPIMIT
- FlicenseNot gradedqualityDmaintenanceAn AI-powered MCP server for intelligent video processing, enabling automated analysis, transition effects, and quality assurance with multi-agent orchestration.2-

video-analyzerofficial
AlicenseNot gradedqualityBmaintenanceMCP server enabling video analysis via scene detection, audio transcription, visual description, and stylistic fingerprinting, with tools for full pipeline execution and storyboard generation.1MIT