com.aicontentdrop由 aicontentdrop.com 发布官方发布者v1.3.6更新于 Oct 24, 2026
Make AI videos, images, ads and short dramas from a description, priced first. Sign in to create.
AI Content Drop 的托管 MCP 服务器，用于先报价再生成 AI 视频、图片和视频广告，并管理看板与竞品广告调研。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/com.aicontentdrop%2Fai-content-drop/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"ai-content-drop": {
"type": "http",
"url": "https://aicontentdrop.com/mcp"
}
}
}Official CLI and TypeScript SDK for AI Content Drop — generate AI video and images across multiple leading models from the terminal or from code.
No runtime dependencies. Works with npx, no install and no API key for
anything read-only.
Python users can install the equally dependency-free official client from PyPI:
Reading the model catalogue, quoting costs, and asking questions need no credential. Generating needs an API key you create at Settings → Integrations — any account works, the free tier includes 10 credits.
Each key can carry a daily credit ceiling, so an agent holding it cannot overspend the budget you set.
Every command prints JSON by default so scripts and agents can parse it; add
--pretty for humans. Failures print JSON to stderr and exit non-zero (2
failure, 3 rate limited).
The SDK maps the same routes: analyzeReference, analyzeReferenceAndWait,
getReference, startDrop, getDrop, listDrops, approveDrop, plus the
pure helpers retryOffersOf and findRetryOffer that read a run for its
retry offers.
Rehearse anything that would cost credits:
Errors throw AcdError with status, code, and retryAfter (on 429).
Billing uses the separate scoped billing contract. It is not part of the public product MCP tool or resource surface. New checkout creation is initially available only on a configured billing sandbox deployment; unavailable catalog entries and unfinished subscription/history/management projections return an explicit unavailable response. These commands do not establish production payment readiness.
Create a key in Settings → Integrations and select each permission needed:
billing:read for status/history, billing:checkout for checkout links, or
billing:manage for portal access. Existing read/generate keys, OAuth tokens,
and catalog-only acd_agent_ tokens do not gain billing permission. A generation
credit cap does not limit purchases.
Checkout requires explicit human initiation and accepted catalog terms. The CLI
prints the owned hosted URL and status URL; a human completes payment in the
browser. Reuse the exact idempotency key and arguments when retrying one intent.
The --sandbox flag simulates generation only and is refused for billing writes;
use a configured billing sandbox host with --base-url instead.
The SDK maps these endpoints through billingCatalog, createBillingCheckout,
billingCheckout, billingStatus, billingHistory, and createBillingPortal.
Supply catalogVersion, skuId, kind, idempotencyKey, and returnTarget
to createBillingCheckout. Neither the SDK nor the CLI opens the returned URL.
The public repository mirrors fourteen focused skills in its root skills/
directory. Use that directory as the source so discovery selects the product
collection directly:
Each skill is independently installable and has a narrow trigger: model selection and quoting, video prompting, image generation, batch execution, error recovery, credits and plans, finished ads, boards, competitor research, the video agent, recreating a reference, short dramas, and hosts that build their own client. See the skills catalogue for the capability map.
POST https://aicontentdrop.com/mcp (Streamable HTTP) — manifest
at /.well-known/mcp.jsonPOST https://aicontentdrop.com/mcp/docs/auth.md/openapi.jsonskills/ — model selection, prompt writing, batch runs,
error handling, credits, image generation, finished ads, boards, competitor
research, the video agent, recreating a reference and short dramas. Also served per skill at
https://aicontentdrop.com/skills/<name>/SKILL.md, indexed at
/skills/index.jsonplugin.json + mcp.json
(Agent Plugins v1.0.0)AGENTS.mdDocumentation https://aicontentdrop.com/developers · TypeScript registry https://www.npmjs.com/package/aicontentdrop · Python registry https://pypi.org/project/aicontentdrop/ · Support [email protected]
MIT licensed.
来源：README.md，提交 ec3dbeb
List models
See which AI video or image models can make a video ad, animate a photo, produce a product clip or generate an image, with the credit cost of one generation. No account needed. The list is live; `count` is the number of models currently offered.
typemax_creditsEstimate credit cost
Price a video or image before making it. Returns the exact credit cost and a quote_id that generate_video and generate_image require. No account needed. Pass the duration and resolution you intend to use; some video models bill per second.
durationmodel_id必填quantityresolutionreference_video_secondsSearch articles
Search AI Content Drop's published guides and model comparisons about AI video generation, prompting, and ad creative.
limitquery必填Get article
Fetch the full text of one published article as markdown, by slug.
slug必填List ad formats
See the ad formats the studio can produce — UGC, talking head, unboxing, tutorial, TV spot, product hero, hyper-motion, try-on and more — with a one-line description, the default aspect and the allowed shot count and duration. No account needed. Pick one before writing a brief.
无需输入参数。
List UGC avatars
See the catalogue creators available for a UGC video — name, style and a portrait URL — and the fields generate_ugc_video accepts. No account needed. A person's own photo can be used instead, with their consent.
无需输入参数。
Estimate ad cost
Price a studio job before making it: a finished ad from a brief or storyboard (kind "ad"), a UGC creator video (kind "ugc"), a generated avatar (kind "avatar") or a competitor-ad decode (kind "decode"). Returns the credit lines, the total and a quote_id that generate_ad, generate_ugc_video, generate_avatar and decode_ad require. No account needed. For an ad, quote exactly the fields you will submit.
kindbriefqualitymodel_tierstoryboardpersona_modeneeds_avatar_genneeds_product_genGenerate video
Make an AI video: a product ad, a vertical clip for social, a cinematic shot, or animate a photo into video (image-to-video). Requires a quote_id from estimate_credit_cost so the price is agreed first; then returns a job id to poll with get_generation. Credits are charged only when the video succeeds. 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.
modelprompt必填durationquote_id必填image_urlresolutionaspect_ratioreference_video_urlGenerate image
Make an AI image: a product still, a thumbnail, a poster, concept art, or a reference frame to animate later. Requires a quote_id from estimate_credit_cost so the price is agreed first; then returns a job id to poll with get_generation (kind "image"). Credits are charged only when the image succeeds. 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.
modelprompt必填quote_id必填image_urlGet generation
Check whether a video or image is finished and get its URL. Poll this after generate_video or generate_image; pass kind "image" for an image job. Reports status, the finished file URL, and the credits charged. 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.
id必填kindList generations
List the account's recent video generations, newest first, with their status and URLs. 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.
limitGet account
Check the signed-in account's remaining credits and current plan name before generating, and get the informational page about plans and entitlement. 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.
无需输入参数。
Write ad storyboard
Turn an ad brief into a storyboard: 1-5 shots with framing, the spoken line, the caption and the duration of each. Costs no credits. Show it to the person, edit it if needed, then price it with estimate_ad_cost and submit it with generate_ad. 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.
brief必填Generate ad
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.
briefmusicqualityquote_id必填canvas_idavatar_url必填model_tierproject_idstoryboardpersona_modeneeds_avatar_genneeds_product_gen另有 3 个Get ad job
Check an ad job: stage and percent while it renders, then the finished video URL, the storyboard sheet, duration, size and the credits charged. Poll every 15 seconds after generate_ad; stop after 15 minutes. 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.
job_id必填Generate UGC video
Make a UGC-style creator video: a catalogue creator (template from list_ugc_avatars) or a person's own photo (image_url) speaks the script with lip-sync, optional voice choice and ambience. Requires a quote_id from estimate_ad_cost with kind "ugc", and image_rights_consent: true given by the person. Returns an id to poll with get_generation. Credits are charged only on success. 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.
voicescript必填ambiencelanguagequote_id必填templateimage_urlimage_rights_consent必填Generate avatar
Generate a creator portrait (Nano Banana) to use as the avatar in generate_ad, checked for hands, face and background defects. Requires a quote_id from estimate_ad_cost with kind "avatar". Finishes within the call; credits are charged only when a portrait comes back. 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.
prompt必填save_asquote_id必填aspect_ratioImport asset
Copy a public image (JPEG, PNG or WebP, at most 10 MB) onto AI Content Drop so it can be used as an avatar, product or photo reference. Returns the hosted URL. Costs no credits. 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.
url必填List brand profiles
List the account's saved brand profiles — name, site, value props, CTA, tone, product images — so ads for the same brand reuse the same facts. 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.
无需输入参数。
Import brand profile
Read a brand's website and save a brand profile from it: name, value props, CTA, tone and product images. Costs no credits. Low-confidence reads are returned for confirmation instead of being saved. 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.
url必填modepersistList boards
List the account's boards (visual canvases), newest first: id, name, revision, card count and the board's page link. Costs no credits. Start here to pick a board or to see that none exists yet. 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.
无需输入参数。
Create board
Create a new, empty board and return it. Costs no credits. Use one board per plan or campaign; cards are added with the add_* tools. 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.
nameGet board
Read one board in full: every card with its type, position, size and data, the edges, and the revision. Generation cards that are still rendering are checked against their jobs on every read. Shows the board as a view; a board already on screen updates itself, so call this to show a board that is not. Costs no credits. 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.
canvas_id必填Rename board
Rename a board. Costs no credits. 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.
name必填revisioncanvas_id必填Get board link
Get the link to a board's page on AI Content Drop so the person can open it in a browser or the host's embedded browser panel. Costs no credits. 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.
canvas_id必填Add text card
Add a text card (a note, an idea, a script line) to a board. The server places it on a grid unless a position is given. Costs no credits. Returns the whole board and the new card. 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.
text必填colortitlewidthheightpositionrevisioncanvas_id必填Add media card
Add an image or video card to a board from a public https URL (an import_asset result, a finished generation's video_url, or an ad's video_url). Costs no credits. Returns the whole board and the new card. 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.
url必填kind必填titlewidthheightsourcecaptionpositionrevisioncanvas_id必填Add frame
Add a labelled frame (a region such as Week 1 or Hooks) to a board. To wrap existing cards in a frame use group_cards instead. Costs no credits. 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.
label必填widthheightpositionrevisioncanvas_id必填Add generation card
Add a draft generation card to a board: a prompt and a model (an id from list_models) that can be rendered later with run_generation_card. Adding it costs nothing; nothing renders until it is run with a quote. Set duration and resolution on the card for a per-second model: the quote for run_generation_card must be taken with them. For a step that builds on an earlier card (a still that becomes a video), pass from_card_id: the new card is connected to that card on the board and, unless it has its own image_url, starts from that card's finished image. 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.
kindmodelwidthheightpromptdurationpositionrevisioncanvas_id必填image_urlresolutionaspect_ratio另有 1 个Connect cards
Connect two cards on a board with a line from one to the next, so the board reads as a flow: a script card to the card that renders it, an idea to each of its variations. Costs no credits. Refuses a card connected to itself, a frame, and a connection that is already there. To make an image card's result the start frame of a new card, add that card with add_generation_card and from_card_id instead. 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.
labelrevisioncanvas_id必填to_card_id必填from_card_id必填Update card
Change a card: merge fields into its data (text or title on a text card; prompt, model, kind, aspect_ratio, duration, resolution or image_url on a generation card; title or caption on a media card; label on a frame), or move and resize it. Costs no credits. status, job_id, job_kind, quote_id, media_url, thumbnail_url, credits_used and error are set by the server when a card runs and are refused here. A per-second model is priced from the card's duration and resolution, so set them before quoting. 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.
datawidthheightcard_id必填positionrevisioncanvas_id必填Move cards
Move one or more cards to new positions on a board. The server places new cards itself; this is for the board view's drag. Costs no credits. 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.
moves必填revisioncanvas_id必填Arrange cards
Lay chosen cards (or the whole board) out as a grid, a row or a column. Costs no credits. 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.
gapidslayout必填revisioncanvas_id必填Group cards
Wrap chosen cards in a labelled frame that encloses them. Returns the board and the new frame. Costs no credits. 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.
ids必填label必填revisioncanvas_id必填Run generation card
Render a generation card: its prompt and model become a video or image job whose result lands in the card. Requires a quote_id from estimate_credit_cost for the card's model and kind (quantity 1), taken with the card's duration and resolution when it has them: per-second models are priced from those, and the quote is verified against the card. A card added with from_card_id and no image_url starts from its source card's finished image; until that card is done the run is refused with nothing charged. Credits are charged only on success; a retry with the same quote_id returns the same job. 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.
card_id必填quote_id必填revisioncanvas_id必填Refresh board
Re-read a board (same answer as get_canvas). Call it every 10 seconds while a generation card is rendering; a finished render sets the card's status to done and its media_url. It opens no new view: a board already on screen refreshes itself. Costs no credits. 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.
canvas_id必填Search competitor ads
Search live competitor ads by keyword on Meta or TikTok: advertiser, copy, hook, call to action, media and run time per ad. Costs no credits. When live data is not available the rows are samples, marked demo: true with a note; never present those as real ads. 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.
sortlimitkeyword必填platformList saved ads
List the competitor ads saved on the account, newest first: id, advertiser, hook, media and whether a decode is stored. Costs no credits. Start here to pick an ad to decode or place on a board. 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.
无需输入参数。
Get saved ad
Read one saved competitor ad in full, with its stored decode (the ad's formula and a recreation prompt) when it has one. Costs no credits; never runs a decode. 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.
ad_id必填Save competitor ad
Keep one ad from search_competitor_ads on the account so it can be decoded and placed on a board. Pass the row exactly as returned. Costs no credits. Saving the same ad twice returns the existing saved ad. 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.
ad必填Decode ad
Decode a saved competitor ad into a reusable formula: hook, script, scenes, audio, call to action and style, plus a generation-ready recreation prompt. Requires a quote_id from estimate_ad_cost with kind "decode" (a flat price). Credits are charged only when the analysis succeeds; an ad decoded before returns its stored decode and charges nothing. 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.
ad_id必填quote_id必填Ad to board
Place a saved competitor ad on a board as a media card (its video or image, the advertiser as title, the hook as caption) with its decoded brief attached when it has one. Costs no credits. Returns the whole board and the new card. 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.
ad_id必填revisioncanvas_id必填已满足适用检查项的 100%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
npx aicontentdrop models --type video --max-credits 15npm install -g aicontentdrop # CLInpm install aicontentdrop # SDKpip install aicontentdropexport ACD_API_KEY=acd_live_…acd models --type video --max-credits 20 # catalogue with credit costsacd cost kling_3_0 --quantity 4 # quote before committingacd ask "which models generate audio?" # natural-language lookupacd me # account and credit balanceacd generate "a golden retriever surfing at sunset" --model kling_3_0 --waitacd status <video_id>acd list --limit 20 # cursor-paginatedacd list --all # follows the cursor for youacd register --name my-agent # read-scoped agent tokenacd analyze ./reference.mp4 --rights own_work # read a clip or image into words (free, capped)acd drop "a 15-second vertical ad in this style" \ --reference ./reference.mp4 --rights own_work \ --lane auto --confirm-each # read it, start the run, print what it sawacd drop "three product videos for Nimbus Tea" # a plain run from a written goalacd drop status <run_id> --notes # phase, credits, each piece's score and verdict, retry offersacd drop retry <run_id> <piece_id> --quote <quote_id> # approve that retry at the quote shownacd generate "…" --model kling_3_0 --sandbox # no provider call, no creditsimport { AiContentDrop } from "aicontentdrop";
const acd = new AiContentDrop({ apiKey: process.env.ACD_API_KEY });
const models = await acd.models({ type: "video", maxCredits: 20 });
// Submit and poll until the render exists. Sends an Idempotency-Key by default,// so a retry after a dropped response cannot charge twice.const video = await acd.generateVideoAndWait( { prompt: "a golden retriever surfing at sunset", aiModel: "kling_3_0" }, { onProgress: (v) => console.error(v.status) },);console.log(video.video_url);
// Pagination handled for youfor await (const item of acd.allVideos()) { console.log(item.id, item.status);}acd billing catalogacd checkout plan --sku subscription:starter:s0:monthly --catalog-version VERSION_FROM_CATALOG --idempotency-key UNIQUE_PURCHASE_INTENT --confirm-purchaseacd checkout topup --sku topup:pack_150 --catalog-version VERSION_FROM_CATALOG --idempotency-key ANOTHER_PURCHASE_INTENT --confirm-purchaseacd billing status CHECKOUT_IDacd billing statusacd billing history --limit 10acd billing portal --idempotency-key UNIQUE_PORTAL_INTENT# Preview the product skills without installing anythingnpx skills add aicontentdrop/aicontentdrop/skills --list
# Install one capabilitynpx skills add aicontentdrop/aicontentdrop/skills \ --skill ai-video-model-picker
# Install the complete AI Content Drop setnpx skills add aicontentdrop/aicontentdrop/skills \ --skill ai-video-model-picker \ --skill video-prompt-writer \ --skill image-generation \ --skill batch-generation-runner \ --skill api-error-handling \ --skill credits-and-plans \ --skill marketing-studio-ad \ --skill canvas-board \ --skill competitor-ad-research \ --skill video-agent \ --skill recreate-reference \ --skill drama-studio \ --skill short-drama-writer \ --skill muse-connector