Ai Content Drop

com.aicontentdropv1.1.0更新於 Sep 30, 2026

Make AI videos and images from a description, on one credit balance. Sign in to generate.

已驗證Streamable HTTP可網頁執行AI & ML

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Ai Content Drop,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "ai-content-drop": {
      "type": "http",
      "url": "https://aicontentdrop.com/mcp"
    }
  }
}

README

aicontentdrop

Official CLI and TypeScript SDK for AI Content Drop — generate AI video and images across 35+ models from the terminal or from code.

No runtime dependencies. Works with npx, no install and no API key for anything read-only.

bash
npx aicontentdrop models --type video --max-credits 15

Install

bash
npm install -g aicontentdrop    # CLInpm install aicontentdrop       # SDK

Authentication

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.

bash
export ACD_API_KEY=acd_live_…

Each key can carry a daily credit ceiling, so an agent holding it cannot overspend the budget you set.

CLI

bash
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 token

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).

Rehearse anything that would cost credits:

bash
acd generate "…" --model kling_3_0 --sandbox   # no provider call, no credits

SDK

ts
import { 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);}

Errors throw AcdError with status, code, and retryAfter (on 429).

For AI agents

  • MCP server: POST https://aicontentdrop.com/mcp (Streamable HTTP) — manifest at /.well-known/mcp.json
  • Docs-only MCP: POST https://aicontentdrop.com/mcp/docs
  • Agent contract: /auth.md
  • OpenAPI 3.1: /openapi.json
  • Python SDK: python/ — same API surface, zero runtime dependencies, on PyPI as aicontentdrop (pip install aicontentdrop)
  • Go SDK: go/ — same API surface, standard library only, go get github.com/aicontentdrop/aicontentdrop/go
  • Skills: skills/ — model selection, prompt writing, batch runs, error handling, credits, image generation. Also served per skill at https://aicontentdrop.com/skills/<name>/SKILL.md, indexed at /skills/index.json
  • Agent plugin: plugin.json + mcp.json (Agent Plugins v1.0.0)
  • Coding-agent rules for this repo: AGENTS.md

Links

Documentation https://aicontentdrop.com/developers · Support [email protected]

MIT licensed.

來源:README.md,提交 dbed23a

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.1.0最新Sep 16, 2026