YouTube Shorts Scraper MCP Server
# YouTube Shorts Scraper MCP Server
[](https://registry.modelcontextprotocol.io/v0/servers?search=com.mambabuilt/mcp-youtube-shorts-scraper&limit=1) [](https://www.npmjs.com/package/@mambalabsdev/mcp-youtube-shorts-scraper) [](https://www.npmjs.com/package/@mambalabsdev/mcp-youtube-shorts-scraper) [](https://github.com/mambalabsdev/mcp-youtube-shorts-scraper/blob/main/LICENSE)
An MCP server for the Mamba Labs YouTube Shorts Scraper actor on Apify. YouTube Shorts as rows, with views, likes, and comments.
## What's Inside
- [What it does](#what-it-does)
- [Quick start](#quick-start)
- [Prerequisites](#prerequisites)
- [Example prompts](#example-prompts)
- [Tool](#tool)
- [Inputs](#inputs)
- [Pricing](#pricing)
- [Full actor documentation](#full-actor-documentation)
- [License](#license)
## What it does
Takes YouTube channels, search terms, or Short links and returns one row per Short with exact views, likes, comment count, publish date, hashtags, and channel, plus a free report row per source.
All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.
## Quick start
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config (`claude_desktop_config.json`), Cursor, or any MCP client:
```json
{
"mcpServers": {
"mamba-youtube-shorts-scraper": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-youtube-shorts-scraper"
],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}
```
Restart the client. The `get_youtube_shorts` tool appears.
## Prerequisites
- Node.js 18 or newer.
- An Apify API token from [console.apify.com/account/integrations](https://console.apify.com/account/integrations), set as `APIFY_TOKEN`. The server lists its tool without a token; a call needs one.
## Example prompts
- "Get the 20 most popular YouTube Shorts from @MrBeast with their like and comment counts."
- "Find YouTube Shorts about iced coffee recipes and list the ones with the most views."
## Tool
`get_youtube_shorts`. One tool. Example arguments:
```json
{
"channels": [
"@MrBeast"
],
"max_shorts_per_source": 5
}
```
## Inputs
Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.
| Input | Type | Required | Description |
|---|---|---|---|
| `channels` | array | no | Channel handles (@MrBeast or MrBeast), channel links (https://www.youtube.com/@MrBeast), or UC channel IDs. Each channel's Shorts tab is read. |
| `search_terms` | array | no | Words to search on YouTube with the Shorts filter, one term per line, for example iced coffee recipe. YouTube orders the results. |
| `shorts` | array | no | Single Shorts: links such as https://www.youtube.com/shorts/sHpEqeSByPI, watch links, youtu.be links, or 11 character video IDs. Each one gets a row with its details. |
| `max_shorts_per_source` | number | no | Shorts to return from each channel or search. YouTube shows about 48 a page. Default 30, maximum 1000. |
| `sort` | string | no | Order of a channel's Shorts tab: latest (default), popular (most viewed), or oldest. Searches keep YouTube's own order. |
| `details` | boolean | no | yes (default): read each Short for exact views, likes, comment count, and publish date, priced per Short with details. no: return only what the list shows (ID, title, rounded views, thumbnail) at the lower list price. Short links always get details. |
| `max_charge_usd` | number | no | Optional. The run stops before a charge that would pass this amount. Report rows are always returned. |
## Pricing
Pay per event on Apify, billed to your Apify account. Prices in USD.
| Event | Free plan | Bronze | Silver | Gold |
|---|---|---|---|---|
| `short-detail-row`, one Short with details | $0.002 | $0.0019 | $0.0018 | $0.0017 |
| `short-row`, one Short from the list only (details off) | $0.001 | $0.00095 | $0.0009 | $0.00085 |
| `apify-actor-start`, per run start | $0.004 | $0.004 | $0.004 | $0.004 |
Source reports, Shorts YouTube says are not available, refused reads, repeats, and refused input are free. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.
## Full actor documentation
[apify.com/mambalabs/youtube-shorts-scraper](https://apify.com/mambalabs/youtube-shorts-scraper)
## License
MIT. See [LICENSE](LICENSE).
TDQS
Scored across 1 tool
With only one tool there is no possibility of misselection; its purpose (fetching YouTube Shorts metadata plus a report row) is explicit and unambiguous. The three input modes (channel tab, search filter, short link) are handled within one clearly documented entry point rather than competing tools.
The single name get_youtube_shorts is a clear verb_noun snake_case pattern that matches the server's stated purpose. No mixed conventions exist to cause confusion.
One tool is thin even for a focused scraper: the three distinct source modes (channel, search, link) and sorting options are all collapsed into a single parameterized call. It works, but a slightly larger set of source-specific tools could be easier to invoke correctly.
As a read-only scraping domain, no create/update/delete operations are needed, and the tool covers the main entry points (channel Shorts tab, filtered search, short links) with rich output fields and sorting. Minor gaps remain around result limits/pagination and any per-video detail or download operation, which an agent would have to work around.