Turn a video link into captioned 9:16 short clips: AI picks the moments, reframes and captions.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer token: an AIClipMaker.org API key (starts with acm_), created under Settings > API keys.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
0-based index from list_clips.
Karaoke active-word effect; 'highlight' = solid box behind it.
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.
Karaoke: words appear as they are spoken.
Drop shadow depth 0-6.
Show one word at a time.
Anton, Montserrat ExtraBold, Verdana, Arial, Impact, Georgia...
44 is the default (M); 34 = S, 56 = L, 70 = XL.
Hex color, e.g. #FFFFFF.
Outline 0-10 (0 needs a shadow to stay readable).
Karaoke active-word color (or box color with effect 'highlight').
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http clip-maker https://aiclipmaker.org/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Bearer token: an AIClipMaker.org API key (starts with acm_), created under Settings > API keys.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.
| Argument | Type | Description |
|---|---|---|
| style | string | |
| effect | string | Karaoke active-word effect; 'highlight' = solid box behind it. |
| job_id* | string | |
| preset | string | 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. |
| reveal | boolean | Karaoke: words appear as they are spoken. |
| shadow | integer | Drop shadow depth 0-6. |
| one_word | boolean | Show one word at a time. |
| position | string | |
| font_name | string | Anton, Montserrat ExtraBold, Verdana, Arial, Impact, Georgia... |
| font_size | integer | 44 is the default (M); 34 = S, 56 = L, 70 = XL. |
| uppercase | boolean | |
| clip_index* | integer | 0-based index from list_clips. |
| font_color | string | Hex color, e.g. #FFFFFF. |
| border_width | integer | Outline 0-10 (0 needs a shadow to stay readable). |
| highlight_color | string | Karaoke active-word color (or box color with effect 'highlight'). |
{
"type": "object",
"required": [
"job_id",
"clip_index"
],
"properties": {
"style": {
"enum": [
"classic",
"karaoke"
],
"type": "string"
},
"effect": {
"enum": [
"none",
"pop",
"glow",
"box",
"highlight"
],
"type": "string",
"description": "Karaoke active-word effect; 'highlight' = solid box behind it."
},
"job_id": {
"type": "string"
},
"preset": {
"enum": [
"default",
"hormozi",
"pill",
"lime",
"oneword",
"clean"
],
"type": "string",
"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."
},
"reveal": {
"type": "boolean",
"description": "Karaoke: words appear as they are spoken."
},
"shadow": {
"type": "integer",
"description": "Drop shadow depth 0-6."
},
"one_word": {
"type": "boolean",
"description": "Show one word at a time."
},
"position": {
"enum": [
"top",
"middle",
"bottom"
],
"type": "string"
},
"font_name": {
"type": "string",
"description": "Anton, Montserrat ExtraBold, Verdana, Arial, Impact, Georgia..."
},
"font_size": {
"type": "integer",
"description": "44 is the default (M); 34 = S, 56 = L, 70 = XL."
},
"uppercase": {
"type": "boolean"
},
"clip_index": {
"type": "integer",
"description": "0-based index from list_clips."
},
"font_color": {
"type": "string",
"description": "Hex color, e.g. #FFFFFF."
},
"border_width": {
"type": "integer",
"description": "Outline 0-10 (0 needs a shadow to stay readable)."
},
"highlight_color": {
"type": "string",
"description": "Karaoke active-word color (or box color with effect 'highlight')."
}
}
}Status of a processing job: 'queued', 'processing', 'completed' or 'failed', with recent log lines and, once completed, the clips.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
}
}The authenticated user's plan and remaining processing minutes. Call before large jobs; process_video fails with quota_exceeded when the balance is insufficient.
No arguments.
{
"type": "object",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
}
}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).
| Argument | Type | Description |
|---|---|---|
| source_url | string | Public video URL, passed through exactly as the user gave it (YouTube watch/short/live URL or a direct video file URL). The server does the downloading. |
| webhook_url | string | Optional public HTTPS URL POSTed once when the job finishes or fails. |
| target_clips | integer | 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). |
| confirm_rights* | boolean | Must be true: the user owns the content or has rights to process it. |
| webhook_secret | string | Optional secret; the webhook body is then HMAC-SHA256 signed (X-AIClipMaker-Signature, also sent as X-OpenShorts-Signature). |
{
"type": "object",
"required": [
"confirm_rights"
],
"properties": {
"source_url": {
"type": "string",
"description": "Public video URL, passed through exactly as the user gave it (YouTube watch/short/live URL or a direct video file URL). The server does the downloading."
},
"webhook_url": {
"type": "string",
"description": "Optional public HTTPS URL POSTed once when the job finishes or fails."
},
"target_clips": {
"type": "integer",
"maximum": 15,
"minimum": 1,
"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)."
},
"confirm_rights": {
"type": "boolean",
"description": "Must be true: the user owns the content or has rights to process it."
},
"webhook_secret": {
"type": "string",
"description": "Optional secret; the webhook body is then HMAC-SHA256 signed (X-AIClipMaker-Signature, also sent as X-OpenShorts-Signature)."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| framing | string | 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. |
| segments* | array | Ordered source segments the new clip is made of. |
| clip_index* | integer | 0-based index from list_clips. |
| snap_to_words | boolean | Snap each boundary onto transcript word boundaries (recommended). |
| reapply_captions | boolean | Burn default captions back on after the recut (default true). |
{
"type": "object",
"required": [
"job_id",
"clip_index",
"segments"
],
"properties": {
"job_id": {
"type": "string"
},
"framing": {
"enum": [
"auto",
"full",
"track"
],
"type": "string",
"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."
},
"segments": {
"type": "array",
"items": {
"type": "object",
"required": [
"start",
"end"
],
"properties": {
"end": {
"type": "number",
"description": "Seconds in the source video."
},
"start": {
"type": "number",
"description": "Seconds in the source video."
}
}
},
"minItems": 1,
"description": "Ordered source segments the new clip is made of."
},
"clip_index": {
"type": "integer",
"description": "0-based index from list_clips."
},
"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)."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 18, 2026.