clipform_render_composition
ActiveTool of io.github.Clipform/mcp-server
Render a specialised video composition to MP4 or PNG - custom animated visuals that clipform_generate_video can't provide, such as geography animations or designed motion graphics. Available composition names and their required input props schemas come from clipform_list_compositions. For narrated Ken Burns slideshows from images, use clipform_generate_video instead. Output formats: mp4 (H.264, best for social media) or png (single frame). Returns a public URL when complete. For multi-render builds (e.g. one clip per quiz question), pass everything in ONE call via items (max 10): all renders fire in parallel and you get one job ID each - then collect the URLs in a single clipform_check_render call with job_ids. Single render: pass compositionId/inputProps at the top level (wait: true blocks and returns the URL; wait: false returns a job ID). Choosing a render tool: for a recognisable form/quiz beat (guess-the-city, this-or-that, mystery reveal, multiple choice, photo montage...) reach for a video template first (clipform_list_video_templates + clipform_render_video_template) - it is a one-call recipe. Use clipform_generate_video for a narrated or audio-synced media montage (images/clips timed to a voice track). Use clipform_render_composition only when neither fits and you need a custom layer stack. A render for a form node is not done until it is attached to that node. Pass node_id (and form_id) so the completed render attaches itself automatically - do not poll clipform_check_render to completion or manually chain clipform_upload_media_asset + clipform_attach_node_media; fire the render and move on. In batch mode, set node_id per item (see items) and form_id once at the top level.
Parameters schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"wait": {
"type": "boolean",
"default": true,
"description": "Single render only: true (default) blocks until the render is ready and returns its URL; false returns a job ID for clipform_check_render. Batch items always run fire-and-poll."
},
"items": {
"type": "array",
"items": {
"type": "object",
"required": [
"compositionId"
],
"properties": {
"node_id": {
"type": "string",
"description": "Form node to attach this item's render to automatically once it completes. Requires the batch's top-level form_id."
},
"captions": {
"type": "array",
"items": {
"type": "object",
"required": [
"start",
"end",
"text"
],
"properties": {
"end": {
"type": "number",
"description": "Segment end time in seconds"
},
"text": {
"type": "string",
"description": "Full segment text"
},
"start": {
"type": "number",
"description": "Segment start time in seconds"
},
"words": {
"type": "array",
"items": {
"type": "object",
"required": [
"word",
"start",
"end"
],
"properties": {
"end": {
"type": "number"
},
"word": {
"type": "string"
},
"start": {
"type": "number"
}
},
"additionalProperties": false
},
"description": "Per-word timestamps within the segment"
}
},
"additionalProperties": false
},
"description": "Word-level captions from clipform_generate_tts - carried onto the attached media asset. Only used when node_id is set."
},
"inputProps": {
"type": "object",
"description": "Props matching the composition's schema - validated strictly",
"additionalProperties": {}
},
"outputFormat": {
"enum": [
"mp4",
"png"
],
"type": "string",
"default": "mp4",
"description": "Output format (default: mp4)"
},
"compositionId": {
"type": "string",
"description": "The composition ID (see clipform_list_compositions)"
}
},
"additionalProperties": false
},
"maxItems": 10,
"minItems": 1,
"description": "Batch mode: multiple renders in one call. All fire in parallel; returns one job ID per item - collect with clipform_check_render (job_ids). Use this whenever rendering more than one clip."
},
"form_id": {
"type": "string",
"format": "uuid",
"description": "The form UUID - required when node_id is set (single render) or any item sets node_id (batch)."
},
"node_id": {
"type": "string",
"description": "Single render only: form node to attach this render to automatically once it completes. Requires form_id. For batch mode, set node_id per item instead."
},
"captions": {
"type": "array",
"items": {
"$ref": "#/properties/items/items/properties/captions/items"
},
"description": "Single render only: word-level captions from clipform_generate_tts, carried onto the attached media asset. Only used when node_id is set. For batch mode, set captions per item instead."
},
"inputProps": {
"type": "object",
"description": "Single render: props object matching the composition's schema from clipform_list_compositions. Validated STRICTLY - unknown or missing props fail with the schema in the error, nothing renders silently with defaults. For map compositions (Map), wide shots (camera.zoom < 9) may round lat/lng to 1 decimal place to improve cache hit rates; close shots and pin drops should keep full precision — the pin lands exactly on `target`.",
"additionalProperties": {}
},
"outputFormat": {
"enum": [
"mp4",
"png"
],
"type": "string",
"default": "mp4",
"description": "Single render: output format (default: mp4)"
},
"compositionId": {
"type": "string",
"description": "Single render: the composition ID. Call clipform_list_compositions to see available options (e.g. 'Slideshow', 'Map', 'Grid'). Use items instead for multiple renders."
}
},
"additionalProperties": false
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
io.github.Clipform/mcp-server
https://github.com/clipform/mcp-server
1/7 registries