MCP YouTube Transcript
by jkawamoto
An MCP server retrieving transcripts of YouTube videos
Runs on your computer★ 495MITUpdated 10 days ago
Install
AI Content Drop
Overview
Description from the maker (original English)
Make AI videos, images, ads and short dramas from a description, priced first. Sign in to create.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiNot measured yet★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs in the cloud
- Transport: Streamable HTTP
- Category: Marketing & social media
- You need to fill in: Authorization
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on the maker’s server: what you ask it goes through their server.
- You fill in yourself:
Authorization
Values marked secret are keys to your account. Never share them or paste them into a chat.
You need
- Runs in the cloudNothing to install; it connects over the internet
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http ai-content-drop https://aicontentdrop.com/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Or copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ai-content-drop": {
"url": "https://aicontentdrop.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"ai-content-drop": {
"type": "http",
"url": "https://aicontentdrop.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Values you fill in
Authorizationsecret HTTP headerBearer acd_live_… — optional. Every tool is listed; the key (or an OAuth sign-in) authorizes the account and generation tools. Generation requires a quote_id from estimate_credit_cost.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
We have not read this server’s tool list yet; we check endpoints in rotation.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified against the domain aicontentdrop.com (the registry checks domain ownership)
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- … Not checked yet
Endpoint responds
Not checked yet; we check endpoints in rotation
- … Not checked yet
Sign-in with OAuth
Not checked yet; we check endpoints in rotation
- … Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint
Compared with others in Marketing & social mediai
- More stars than 0% of the other 2987 servers in this category
- Published to the registry more recently than 53% of the other 2987 servers in this category
- Basic checks equal to or better than 100% of the other 2987 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is AI Content Drop safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
You need to fill in: Authorization
Does it run on my computer or in the cloud?
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
Is it still maintained?
The GitHub repo last changed –, and the latest version (1.3.6) reached the registry 27 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
What can I use instead?
In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Google Analytics MCP
by surendranb
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
Runs on your computer★ 244MITUpdated 10 days ago
Install
BibiGPT YouTube Video Summarizer
by JimmyLv
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
Runs in the cloud★ 137MITUpdated 10 days ago
Install
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
aicontentdrop
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.
npx aicontentdrop models --type video --max-credits 15Install
npm install -g aicontentdrop # CLInpm install aicontentdrop # SDK
Python users can install the equally dependency-free official client from PyPI:
pip install aicontentdropAuthentication
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.
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
acd models --type video --max-credits 20 # catalogue with credit costsacd cost kling_3_0 --quantity 4 # quote before committing acd ask "which models generate audio?" # natural-language lookup acd me # account and credit balance acd generate "a golden retriever surfing at sunset" --model kling_3_0 --wait acd status acd list --limit 20 # cursor-paginated acd list --all # follows the cursor for you acd 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).
The video agent, from a reference
acd 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 saw acd drop "three product videos for Nimbus Tea" # a plain run from a written goal acd drop status --notes # phase, credits, each piece's score and verdict, retry offers acd drop retry --quote # approve that retry at the quote shown
| Command | What it does | ||||
|---|---|---|---|---|---|
| `analyze [--rights own_work\ | licensed\ | permission]` | POST /v1/engine/analyze. Prints the class with its confidence, the summary, the shots (index, size, camera, action, tags), cast, look and lines. Words only; no frame comes back. A video needs --rights. | ||
| `drop " " [--reference ] [--lane auto\ | marketing\ | cinematic\ | ugc\ | drama] [--budget N] [--confirm-each]` | With a reference: reads it, then POST /v1/engine/chat with the reference on the brief. Without: POST /v1/engine/runs. Prints the run_id and what it saw. Starting charges nothing. |
drop status [--notes] | GET /v1/engine/runs/:id. Phase, status, credits, each piece with its score and verdict; --notes adds the reasons and the Director's notes. Lists every retry offer with task_id, quote_id and credits. | ||||
drop retry --quote | Finds the priced retry waiting on that piece and approves it through POST /v1/engine/runs/:id/approve, only when its current quote_id is the one given (the one drop status showed the person). Without --quote it sends nothing and refuses (--accept-quote alone names no price and is refused too); when the retry was priced again it approves nothing, exits 2 and prints the current quote_id and credits (quote_mismatch). |
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:
acd generate "…" --model kling_3_0 --sandbox # no provider call, no creditsSDK
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 you for await (const item of acd.allVideos()) { console.log(item.id, item.status); }
Errors throw AcdError with status, code, and retryAfter (on 429).
Billing handoffs
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.
acd billing catalogacd checkout plan --sku subscription:starter:s0:monthly --catalog-version VERSION_FROM_CATALOG --idempotency-key UNIQUE_PURCHASE_INTENT --confirm-purchase acd checkout topup --sku topup:pack_150 --catalog-version VERSION_FROM_CATALOG --idempotency-key ANOTHER_PURCHASE_INTENT --confirm-purchase acd billing status CHECKOUT_ID acd billing status acd billing history --limit 10 acd billing portal --idempotency-key UNIQUE_PORTAL_INTENT
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.
Install the agent skills
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:
# Preview the product skills without installing anythingnpx skills add aicontentdrop/aicontentdrop/skills --list
Install one capability
npx skills add aicontentdrop/aicontentdrop/skills \ --skill ai-video-model-picker
Install the complete AI Content Drop set
npx 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
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.
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 - Skills:
skills/— 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 athttps://aicontentdrop.com/skills/ /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 · TypeScript registry https://www.npmjs.com/package/aicontentdrop · Python registry https://pypi.org/project/aicontentdrop/ · Support
MIT licensed.