Skip to main content
Glama
paulet4a-commits

webdatatools-social-mcp

by paulet4a-commits
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

youtube_search_scraper

Scrape YouTube search results to get videos, channels, or playlists with titles, views, duration, and publish time—no API key or quota needed.

Instructions

YouTube Search Results Scraper returns videos, channels or playlists for any keyword, with title, views, duration, channel and publish time — no API key, no quota. Billed to your own Apify account: ~$0.0005 per result (Apify free-plan price, lower on paid plans).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoResult type — Choose what kind of result to return: all mixes videos, channels and playlists; video/channel/playlist restrict the search server-side to one kind (verified live against YouTube's search endpoint). Options: all = All (videos, channels, playlists); video = Videos only; channel = Channels only; playlist = Playlists only.video
regionNoRegion — Country code sent to YouTube as gl, e.g. US. Affects which results and trending content YouTube considers local.US
sortByNoSort by — How to order results. relevance (default) and views are applied by YouTube's server and verified live (views produces a clean view-count-descending order). date and rating could not be verified server-side during testing — for those two the Actor instead re-sorts the page(s) it already fetched by parsed publish time client-side, which is a best-effort approximation, not a true site-wide sort; see the README. Options: relevance = Relevance (default); date = Upload date (best-effort, client-side); views = View count (verified server-side); rating = Rating (best-effort, unreliable — YouTube hides ratings).relevance
queriesYesSearch queries — Enter the search terms to run on YouTube, one row is returned per result, e.g. web scraping tutorial. One dataset row is produced per matching video, channel or playlist. Example: ["web scraping tutorial"].
durationNoDuration — Only return videos of this length: short is under 4 minutes, medium is 4-20 minutes, long is over 20 minutes. Verified live against YouTube's own duration filter. Ignored when Result type is channel or playlist. Options: any = Any length; short = Short (< 4 min); medium = Medium (4-20 min); long = Long (> 20 min).any
languageNoInterface language — Language code sent to YouTube as hl, e.g. en. Affects relative time text ("2 days ago") and UI strings the parser reads.en
uploadDateNoUpload date — Only return videos uploaded within this window, e.g. week for the last 7 days. Verified live against YouTube's own upload-date filter. Ignored when Result type is channel or playlist. Options: any = Any time; hour = Last hour; today = Today; week = This week; month = This month; year = This year.any
maxResultsPerQueryNoMax results per query — Enter how many results to return per search query, e.g. 50. The Actor pages through YouTube's search continuations until it reaches this number or YouTube runs out of results.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose unusual operational context: no API key or quota needed, and results are billed to the caller's Apify account at roughly $0.0005 per result. It omits auth setup details, rate limits, failure behavior, and pagination cutoffs (the maxResultsPerQuery cap lives only in the schema).

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?

Two tight sentences: capability and output fields first, then cost and no-key/no-quota caveat. Nothing is redundant and the most decision-relevant facts are front-loaded.

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 an 8-parameter tool with a fully documented schema and no output schema, the description covers purpose, output shape, and billing model adequately. It leaves the agent without explicit sibling routing or auth prerequisites, which is the main remaining gap.

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 the parameter docs are exceptionally detailed (live-verified sort behaviors, duration boundaries, ignored-when-channel caveats), so the schema already does the heavy lifting. The description adds no parameter-level meaning beyond what the schema states.

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

Purpose4/5

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

States a specific verb and resource: scrapes YouTube search results (videos, channels, playlists) for any keyword, and lists the returned fields. It is clearly distinguishable from sibling lookups like youtube_video_details or youtube_channel_videos by being keyword-driven, but it never names an alternative to sharpen the contrast.

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

Usage Guidelines3/5

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

Usage is implied by 'for any keyword' — use it when you need keyword-based YouTube search rather than direct ID lookups. There is no explicit when-to-use, when-not-to-use, or named alternative among the nine siblings, so the agent must infer the routing.

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