AIClipMaker.org
Turn a video link into captioned 9:16 short clips: AI picks the moments, reframes and captions.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"clip-maker": {
"url": "https://aiclipmaker.org/mcp"
}
}
}Remote endpoints
https://aiclipmaker.org/mcpstreamable-httpWhat it can do
Tool inventory
Tools (6)
🟢process_video(source_url, confirm_rights, webhook_url, webhook_secret, target_clips)
Start clipping a video from its URL. AIClipMaker.org downloads the source itself, transcribes it, finds the most viral moments with AI and renders vertical (9:16) clips. Captions are burned by default. Takes the URL as the user gave it; the video does not need to be opened or transcribed beforehand. Returns a job_id immediately — the work takes minutes; poll get_job_status or pass webhook_url to be called back. The caller must own the content or hold the rights to process it (confirm_rights).
Input Schema
{
"type": "object",
"properties": {
"source_url": {
"type": "string",
"description": "Public video URL, passed through exactly as the user gave it (YouTube watch/short/live URL, TikTok video URL, or a direct video file URL). The server does the downloading."
},
"confirm_rights": {
"type": "boolean",
"description": "Must be true: the user owns the content or has rights to process it."
},
"webhook_url": {
"type": "string",
"description": "Optional public HTTPS URL POSTed once when the job finishes or fails."
},
"webhook_secret": {
"type": "string",
"description": "Optional secret; the webhook body is then HMAC-SHA256 signed (X-AIClipMaker-Signature, also sent as X-OpenShorts-Signature)."
},
"target_clips": {
"type": "integer",
"minimum": 1,
"maximum": 15,
"description": "How many clips to aim for. A target, not a guarantee: fewer come back when the material doesn't hold them. Default: the AI decides (usually 2-6)."
}
},
"required": [
"confirm_rights"
]
}🟢get_job_status(job_id)
Status of a processing job: 'queued', 'processing', 'completed' or 'failed', with recent log lines and, once completed, the clips.
Input Schema
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
}
},
"required": [
"job_id"
]
}🟢list_clips(job_id)
The clips of a completed job, with titles, platform-ready descriptions and download URLs. In MCP Apps-capable clients the result also renders as an interactive clip picker.
Input Schema
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
}
},
"required": [
"job_id"
]
}🟢get_quota
The authenticated user's plan and remaining processing minutes. Call before large jobs; process_video fails with quota_exceeded when the balance is insufficient.
Input Schema
{
"type": "object",
"properties": {}
}🟡add_subtitles(job_id, clip_index, preset, style, position, ...)
Re-style the captions of one clip (clips already ship with the 'default' preset). Easiest: pass a preset; any other field you send overrides that part of it. Without a preset, style 'karaoke' highlights the active word.
Input Schema
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"clip_index": {
"type": "integer",
"description": "0-based index from list_clips."
},
"preset": {
"type": "string",
"enum": [
"default",
"hormozi",
"pill",
"lime",
"oneword",
"clean"
],
"description": "default: Anton caps, yellow active word. hormozi: words appear as spoken, yellow active word. pill: purple box behind the active word. lime: lime box behind the active word. oneword: one big word at a time. clean: no outline, soft shadow, sentence case."
},
"style": {
"type": "string",
"enum": [
"classic",
"karaoke"
]
},
"position": {
"type": "string",
"enum": [
"top",
"middle",
"bottom"
]
},
"font_size": {
"type": "integer",
"description": "44 is the default (M); 34 = S, 56 = L, 70 = XL."
},
"font_name": {
"type": "string",
"description": "Anton, Montserrat ExtraBold, Verdana, Arial, Impact, Georgia..."
},
"font_color": {
"type": "string",
"description": "Hex color, e.g. #FFFFFF."
},
"highlight_color": {
"type": "string",
"description": "Karaoke active-word color (or box color with effect 'highlight')."
},
"effect": {
"type": "string",
"enum": [
"none",
"pop",
"glow",
"box",
"highlight"
],
"description": "Karaoke active-word effect; 'highlight' = solid box behind it."
},
"reveal": {
"type": "boolean",
"description": "Karaoke: words appear as they are spoken."
},
"one_word": {
"type": "boolean",
"description": "Show one word at a time."
},
"shadow": {
"type": "integer",
"description": "Drop shadow depth 0-6."
},
"border_width": {
"type": "integer",
"description": "Outline 0-10 (0 needs a shadow to stay readable)."
},
"uppercase": {
"type": "boolean"
}
},
"required": [
"job_id",
"clip_index"
]
}🔴recut_clip(job_id, clip_index, segments, snap_to_words, reapply_captions, ...)
Re-render one clip from a new list of source-video segments (the same engine behind the dashboard's clip editor). Times are seconds in the ORIGINAL source video: start from the clip's source_segments in list_clips (e.g. end 5 s earlier = lower the last end by 5). Segments are concatenated in the given order, so you can trim, extend, drop a dead moment in the middle, or reorder. Segments inside the clip's original range re-render in seconds; going outside needs the retained source video and re-runs the reframe engine.
Input Schema
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"clip_index": {
"type": "integer",
"description": "0-based index from list_clips."
},
"segments": {
"type": "array",
"items": {
"type": "object",
"properties": {
"start": {
"type": "number",
"description": "Seconds in the source video."
},
"end": {
"type": "number",
"description": "Seconds in the source video."
}
},
"required": [
"start",
"end"
]
},
"minItems": 1,
"description": "Ordered source segments the new clip is made of."
},
"snap_to_words": {
"type": "boolean",
"description": "Snap each boundary onto transcript word boundaries (recommended)."
},
"reapply_captions": {
"type": "boolean",
"description": "Burn default captions back on after the recut (default true)."
},
"framing": {
"type": "string",
"enum": [
"auto",
"full",
"track"
],
"description": "Layout override: 'full' shows the whole source frame (no side-cropping), 'track' forces the subject-tracking crop, 'auto' resets to the AI classifier. Omit to keep the clip's current framing. Non-auto values re-run the reframe engine and need the retained source video."
}
},
"required": [
"job_id",
"clip_index",
"segments"
]
}Community
Evidence