Skip to main content
Glama
YouTube Shorts Scraper MCP Server

YouTube Shorts Scraper MCP Server

Get YouTube Shorts

get_youtube_shorts
Read-onlyIdempotent

Extract YouTube Shorts from channel tabs, filtered searches, or links and return exact views, likes, comments, dates, hashtags, and channel data for analysis.

Instructions

Read YouTube Shorts from channel Shorts tabs, from a YouTube search with the Shorts filter, or from Short links. Returns one row per Short with exact views, likes, comment count, publish date, hashtags, and channel, plus a free report row per source. Channels can be sorted by latest, popular, or oldest.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_youtube_shorts"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoOrder of a channel's Shorts tab: latest (default), popular (most viewed), or oldest. Searches keep YouTube's own order.
shortsNoSingle 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.
detailsNoyes (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.
channelsNoChannel handles (@MrBeast or MrBeast), channel links (https://www.youtube.com/@MrBeast), or UC channel IDs. Each channel's Shorts tab is read.
search_termsNoWords to search on YouTube with the Shorts filter, one term per line, for example iced coffee recipe. YouTube orders the results.
max_charge_usdNoOptional. The run stops before a charge that would pass this amount. Report rows are always returned.
max_shorts_per_sourceNoShorts to return from each channel or search. YouTube shows about 48 a page. Default 30, maximum 1000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, open-world and non-destructive traits, so the bar is lower, and the description still adds real value: it discloses the per-Short pricing model with a cheaper list-only mode, the cost ceiling that halts a run, and that report rows are always returned even when the charge cap triggers. It doesn't discuss failure modes or empty-result behavior, but the cost semantics are unusually well surfaced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with what is read and what is returned, then cost behavior. No filler, no restatement of the title, and the most decision-relevant details (pricing tiers, report rows) are present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return-shape burden and specifies the columns per row plus report rows. For a seven-parameter tool with zero required fields, the one notable omission is an explicit statement that some source argument is needed to do anything.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter including sort, details, max_charge_usd and max_shorts_per_source is already documented in the schema. The description restates the source modes but adds no format or constraint detail beyond what the schema provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read YouTube Shorts') and enumerates the three distinct input modes it supports: channel Shorts tabs, YouTube search with the Shorts filter, and direct Short links. An agent immediately knows what this tool consumes and produces (one row per Short with views, likes, comments, date, hashtags, channel).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The mapping between input type and behavior is spelled out ('from channel Shorts tabs, from a YouTube search with the Shorts filter, or from Short links'), and the sort parameter is scoped explicitly to channels while searches keep YouTube's order. What's missing is a clear statement that at least one of channels/search_terms/shorts must be supplied, which matters given zero required parameters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools