ai-content-drop

generate_ad

Idempotent

Make a finished video ad — multi-shot, with a speaking creator, product shots, captions and an optional music bed — from a brief or a storyboard plus an avatar image and a product image. Requires a quote_id from estimate_ad_cost for exactly these fields; returns a job_id to poll with get_ad_job. Credits are charged only when the ad succeeds, and never more than the quote. SIGN-IN REQUIRED: connect this server with OAuth (the host prompts for it), or add an API key header "Authorization: Bearer acd_live_…" created at https://aicontentdrop.com/settings/integrations.

Input Schema

TableJSON Schema

Name	Required	Description
`brief`	No	The ad brief: brandName, brandOneLiner, valueProps (1-8 strings), cta, intent, format (an id from list_ad_formats), shotCount (1-5), totalDurationSec (5-20), aspect (9:16 \| 16:9 \| 1:1), language, quality (fast \| premium), modelTier (standard \| cinematic), garmentImageUrl for the try-on formats.
`music`	No	Optional music bed.
`quality`	No	Lip-sync tier. premium costs more per talking shot. Defaults to the brief's quality, else fast.
`quote_id`	Yes	The quote_id from estimate_ad_cost for these exact fields (kind ad). Required.
`canvas_id`	No	Optional board id (from list_canvases or create_canvas): the ad is placed on it as a generation card that fills in when the render lands.
`avatar_url`	Yes	Public https URL of the creator's reference image (a catalogue portrait, a generate_avatar result, or an import_asset URL).
`model_tier`	No	cinematic renders on Seedance with director-grade camera work and costs more per shot; needs the brief.
`project_id`	No	Optional studio project (uuid) to file the run under.
`storyboard`	No	The storyboard returned by write_ad_storyboard, as is or edited. When present it is what renders; the brief is optional alongside it.
`persona_mode`	No	synthetic lets the studio substitute one consistent generated creator for the avatar; exact-avatar (default) keeps the avatar as given.
`needs_avatar_gen`	No	True when the avatar still has to be generated (billed as a line).
`needs_product_gen`	No	True when the product still has to be generated (billed as a line).
`product_image_url`	Yes	Public https URL of the product image.
`avatar_description`	No	Optional one-line identity note for the creator (20-500 characters).
`product_description`	No	Optional one-line product note (10-500 characters).

Output Schema

TableJSON Schema

Name	Required	Description
`job_id`	Yes	Poll this with get_ad_job.
`status`	Yes
`replayed`	Yes	True when this quote_id had already been submitted and the original job was returned.
`next_step`	Yes
`studio_url`	No	The job's page in the studio on AI Content Drop.
`credits_quoted`	Yes	The ceiling fixed by the quote.
`poll_after_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 8, 2026

removedOutput schema / properties / run_id

Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}

addedOutput schema / properties / studio_url

Added value: +{
+  "description": "The job's page in the studio on AI Content Drop.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed1 schema field changedSep 30, 2026

changedInput schema / properties / brief / description

Previous value: -"The ad brief: brandName, brandOneLiner, valueProps (1-8 strings), cta, intent, format (an id from list_ad_formats), shotCount (2-5), totalDurationSec (6-20), aspect (9:16 | 16:9 | 1:1), language, quality (fast | premium), modelTier (standard | cinematic), garmentImageUrl for the try-on formats."New value: +"The ad brief: brandName, brandOneLiner, valueProps (1-8 strings), cta, intent, format (an id from list_ad_formats), shotCount (1-5), totalDurationSec (5-20), aspect (9:16 | 16:9 | 1:1), language, quality (fast | premium), modelTier (standard | cinematic), garmentImageUrl for the try-on formats."

AddedSep 11, 2026

TDQS

Score is being calculated.

All ai-content-drop tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.