Skip to main content
Glama

YouTube Comments Scraper

youtube_comments

Scrape YouTube comments and replies from videos, Shorts, channels, playlists or searches, capturing text, likes, author, pinned and creator-hearted flags for sentiment analysis and social listening.

Instructions

Scrape YouTube comments and replies fast: comment text, likes, author, pinned and creator-hearted flags, from videos, Shorts, channels, playlists or search. Sort by top or newest. No YouTube API key and no browser. Use this for sentiment analysis, social listening and community research. Van Born Labs. $1.00 per 1,000 comments, billed to your Apify account.

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": "youtube_comments"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortByNoYouTube's own comment ordering. Options: top = Top comments; newest = Newest first.top
videosNoWatch, youtu.be, Shorts, live URLs or bare video IDs. Channel/playlist URLs pasted here are expanded too.
channelsNoChannel URLs or @handles (latest videos) and playlist URLs. Comments of their videos are scraped.
maxCommentsNoHard cap on comments + replies scraped (and charged) in this run. Defaults to 10 in this MCP server to keep runs cheap.
searchTermsNoScrape comments from the top video results of these YouTube searches.
includeRepliesNoAlso scrape replies to each comment (each reply counts as one result).
maxConcurrencyNoParallel requests.
maxVideosPerSourceNoHow many videos to take from each channel, playlist or search term.
proxyConfigurationNoApify Proxy (datacenter) is used by default.
maxCommentsPerVideoNoStop after this many top-level comments on each video.
residentialFallbackNoRetry blocked requests through residential proxy (no extra cost to you).
maxRepliesPerCommentNoOnly used when replies are included.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag openWorldHint=true, readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: a concrete cost model ($1.00 per 1,000 comments billed to the Apify account), no API key or browser requirement, and the existence of a residential proxy fallback. It does not describe pagination or failure modes on private/deleted videos, keeping it below 5.

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

Conciseness4/5

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

Front-loaded with capability and sources, then sorting, then prerequisites, then pricing — a sensible order with little waste. The vendor name 'Van Born Labs' and the 'fast' qualifier are marketing filler that could be dropped.

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?

For a 12-parameter scraper with no output schema, the description usefully enumerates the returned data fields and the accepted input sources, and discloses the pricing model. It leaves cost/volume interaction (maxComments default of 10, maxConcurrency) entirely to the schema, which is acceptable given full schema coverage.

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 description coverage is 100% and each parameter already documents itself, including defaults and enum values. The description only echoes the sortBy enum ('top or newest') and adds no format or syntax detail beyond the schema, so the 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?

Uses a specific verb (Scrape) with a specific resource (YouTube comments and replies) and immediately enumerates the returned fields (text, likes, author, pinned, creator-hearted) and the supported sources (videos, Shorts, channels, playlists, search). An agent can tell this apart from youtube_video_details without opening the schema.

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?

Gives explicit use cases (sentiment analysis, social listening, community research) and a differentiator (no API key, no browser), which frames when to pick this tool. It stops short of naming a sibling alternative or stating when not to use it, so it lands at a clear 4 rather than a 5.

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