YouTube Discovery by Apoth3osis

Name: YouTube Discovery
Brand: Apoth3osis
SKU: 6a42b0dbb93930241f4b9932
Price: 0.05 USD
Availability: InStock

YouTube Discovery

Connector

Available ActionsEach successful request consumes credits as outlined below.

search^5crget_video_details^5crget_trending_videos^5crget_channel_details^5crlist_channel_playlists^5crlist_playlist_items^5crlist_public_comments^5crlist_video_categories^5crlist_supported_languages^5crlist_supported_regions^5cr

Details

Tap into the full world of public YouTube data straight from your agent. Search billions of videos, channels, and playlists by topic, keyword, channel, date, language, region, livestream status, captions, duration, and license, then pull rich metadata and statistics like view counts, like counts, comment counts, subscriber counts, durations, tags, and topics. Track trending videos by country and category, browse the contents of any public playlist, and read public comment threads to gauge audience sentiment. Ideal for content research, competitive analysis, SEO and keyword discovery, influencer and channel vetting, brand and media monitoring, and trend spotting.

Use Cases

Search YouTube videos by topic keyword and advanced filters, Discover trending videos by country and category, Vet channels by subscriber and view statistics, Research competitor content and posting cadence, Find videos with captions or Creative Commons licenses, Analyze public comment threads for audience sentiment, Browse playlist contents for content curation, Build SEO and keyword discovery workflows, Monitor brand and topic mentions across YouTube, Pull video statistics for performance benchmarking

Dynamic MCP Setup

Connect once through AgentPMT Dynamic MCP, then use approved tools from the same agent connection.

30 Second Setup

STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections.

npm install -g @agentpmt/mcp-routeragentpmt-setup

Hosted Streamable HTTPS

MCP endpoint for browser-based apps like ChatGPT, Claude, Grok, or any time you want a streamable connection with no local install.

https://api.agentpmt.com/mcp

Config Example

Use the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.

Full connection guide

{
  "mcpServers": {
    "agentpmt": {
      "type": "streamable-http",
      "url": "https://api.agentpmt.com/mcp",
      "headers": {
        "Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
        "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
      }
    }
  }
}

Need client videos, organization controls, audit details, and the full feature overview?

More About Dynamic MCP

Actions(10)

search^5cr27 params

Search public YouTube videos, channels, or playlists with filters and pagination.

querystring

Search query. Required unless another selector such as channel_id, topic_id, video_category_id, location, or event_type is provided.

resource_typesarray

Resource types to search. Defaults to video.

Array of: string

max_resultsinteger

Maximum results to return, 1 to 50. Defaults to 10.

page_tokenstring

Pagination token returned by a prior search.

orderstring

Result order.

Values:

dateratingviewCountrelevancetitlevideoCount

safe_searchstring

Safe search level.

Values:

nonemoderatestrict

published_afterstring

Only include resources published after this RFC3339 timestamp.

published_beforestring

Only include resources published before this RFC3339 timestamp.

region_codestring

ISO 3166-1 alpha-2 region code for localized search results.

relevance_languagestring

ISO 639-1 language code for relevance ranking.

channel_idstring

Limit search to a public channel id.

channel_typestring

Channel search filter; valid only when searching channels.

Values:

anyshow

topic_idstring

Limit search to a YouTube topic id.

event_typestring

Livestream event filter for video searches.

Values:

upcominglivecompleted

locationstring

Latitude and longitude for location-based video search, formatted as lat,lng.

location_radiusstring

Radius for location-based search, such as 10km or 5mi. Required with location.

video_captionstring

Caption availability filter for video searches.

Values:

anyclosedCaptionnone

video_category_idstring

Video category id for video searches.

video_definitionstring

Video definition filter.

Values:

anystandardhigh

video_dimensionstring

Video dimension filter.

Values:

any2d3d

video_durationstring

Video duration filter.

Values:

anyshortmediumlong

video_embeddablestring

Set to true to return only embeddable videos.

Values:

true

video_licensestring

Video license filter.

Values:

anyyoutubecreativeCommon

video_paid_product_placementstring

Set to true to filter videos with paid product placement.

Values:

true

video_syndicatedstring

Set to true to return videos playable outside YouTube.

Values:

true

video_typestring

Video type filter.

Values:

anymovieepisode

include_video_detailsboolean

If true, enrich current-page video search results with public video details.

get_video_details^5cr1 param(1 required)

Retrieve public metadata and statistics for up to 50 videos.

video_idsrequiredarray

One to 50 YouTube video ids.

Array of: string

get_trending_videos^5cr5 params

Retrieve public trending videos by region or category.

region_codestring

ISO 3166-1 alpha-2 region code.

video_category_idstring

Video category id.

max_resultsinteger

Maximum videos to return, 1 to 50.

page_tokenstring

Pagination token.

hlstring

Localized language code for returned category metadata when supported.

get_channel_details^5cr3 params

Retrieve one public channel by channel id, handle, or legacy username.

channel_idstring

YouTube channel id.

channel_handlestring

YouTube channel handle, with or without @.

channel_usernamestring

Legacy YouTube username.

list_channel_playlists^5cr4 params(1 required)

List public playlists for a channel.

channel_idrequiredstring

YouTube channel id.

max_resultsinteger

Maximum playlists to return, 1 to 50.

page_tokenstring

Pagination token.

hlstring

Localized language code.

list_playlist_items^5cr3 params(1 required)

List public items in a playlist.

playlist_idrequiredstring

YouTube playlist id.

max_resultsinteger

Maximum items to return, 1 to 50.

page_tokenstring

Pagination token.

list_public_comments^5cr9 params

List public comment threads for a video, channel, or explicit thread ids.

video_idstring

YouTube video id.

channel_idstring

YouTube channel id for all related threads.

thread_idsarray

Explicit comment thread ids.

Array of: string

include_repliesboolean

If true, include embedded replies returned by YouTube.

text_formatstring

Returned comment text format.

Values:

plainTexthtml

comment_orderstring

Comment thread order when listing by video or channel.

Values:

timerelevance

search_termsstring

Search terms for public comment thread text.

max_resultsinteger

Maximum comment threads to return, 1 to 100.

page_tokenstring

Pagination token.

list_video_categories^5cr3 params

List public YouTube video categories by region or explicit ids.

region_codestring

ISO 3166-1 alpha-2 region code.

category_idsarray

Explicit category ids.

Array of: string

hlstring

Localized language code.

list_supported_languages^5cr1 param

List supported YouTube interface languages.

hlstring

Localized language code for returned names.

list_supported_regions^5cr1 param

List supported YouTube regions.

hlstring

Localized language code for returned names.

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "6a42b0dbb93930241f4b9932",
    "parameters": {
      "action": "search"
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "6a42b0dbb93930241f4b9932",
    "parameters": {
        "action": "search"
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "6a42b0dbb93930241f4b9932",
  parameters: {
    "action": "search"
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "6a42b0dbb93930241f4b9932",
  parameters: {
    "action": "search"
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

Usage Instructions

Usage guidance provided directly by the developer for this product.

YouTube Discovery

Search and inspect public YouTube data: videos, channels, playlists, comment threads, categories, languages, and regions. Returns public metadata only (no media downloads, no private owner data).

Actions

`search`

Find videos, channels, and/or playlists. Provide at least one selector: query, channel_id, topic_id, video_category_id, location (with location_radius), or event_type.

Common inputs:

resource_types: array of video / channel / playlist (default ["video"])
max_results: 1-50 (default 10)
order: relevance | date | rating | viewCount | title | videoCount
page_token: cursor from a prior page
published_after / published_before: RFC3339, e.g. 2026-01-01T00:00:00Z
region_code (ISO 3166-1 alpha-2), relevance_language (ISO 639-1), safe_search (none|moderate|strict)
include_video_details: true to enrich video results with stats, duration, license, captions, tags, and topics

Video-only filters (require resource_types:["video"]): event_type, location + location_radius, video_caption, video_category_id, video_definition, video_dimension, video_duration, video_embeddable, video_license, video_paid_product_placement, video_syndicated, video_type. channel_type requires resource_types:["channel"].

`get_video_details`

Required: video_ids (array, 1-50) of 11-character video IDs.

`get_trending_videos`

Optional: region_code, video_category_id, max_results (1-50), page_token, hl.

`get_channel_details`

Exactly one of: channel_id, channel_handle (e.g. @name), channel_username (legacy).

`list_channel_playlists`

Required: channel_id. Optional: max_results (1-50), page_token, hl.

`list_playlist_items`

Required: playlist_id. Optional: max_results (1-50), page_token.

`list_public_comments`

Exactly one of: video_id, channel_id, thread_ids (array). Optional: include_replies, text_format (plainText|html), comment_order (time|relevance), search_terms, max_results (1-100), page_token.

`list_video_categories`

Exactly one of: region_code, category_ids (array). Optional: hl.

`list_supported_languages` / `list_supported_regions`

Optional: hl.

Examples

{"action":"search","query":"home espresso","resource_types":["video"],"order":"viewCount","max_results":5,"include_video_details":true}

{"action":"get_video_details","video_ids":["dQw4w9WgXcQ","9bZkp7q19f0"]}

{"action":"get_trending_videos","region_code":"US","video_category_id":"10","max_results":10}

{"action":"get_channel_details","channel_handle":"@jameshoffmann"}

{"action":"list_public_comments","video_id":"dQw4w9WgXcQ","comment_order":"relevance","max_results":20}

Pagination

Responses include next_page_token / prev_page_token when more pages exist. Pass it back as page_token. One page is fetched per call.

Response

Each action returns its collection (results, videos, channels, playlists, playlist_items, comment_threads, categories, languages, or regions) plus page_info. Items use snake_case fields and include a ready-to-open youtube_url. Video items expose view_count, like_count, comment_count, duration, tags, category_id, topic_categories, caption availability, and live details; channels expose subscriber_count, video_count, view_count, and uploads_playlist_id (pass it to list_playlist_items to page a channel's full upload history).

Limits

Public metadata only. Cannot download audio, video, captions, or thumbnails; cannot read private channel-owner analytics; cannot create, edit, delete, upload, or moderate content.

About this Product

Discover everything happening on YouTube, straight from your agent

YouTube Discovery gives your AI agent structured, on-demand access to the public side of the world's largest video platform. Search across billions of videos, channels, and playlists, pull detailed metadata and performance statistics, surface what is trending in any country, and read public comment threads, all from a single connection with no API keys or quotas to manage.

What you can do

Search videos, channels, and playlists by keyword, topic, channel, publish date, language, and region.
Pull rich video metadata and statistics including view counts, like counts, comment counts, duration, tags, categories, and topics for up to 50 videos at once.
Profile any channel by ID, handle, or username to see subscriber counts, total views, video counts, and country.
Track trending videos by country and category to spot momentum as it happens.
Browse playlists and list every video inside them for content curation and competitive teardowns.
Read public comment threads on any video or channel to gauge audience sentiment and recurring questions.
Look up reference data such as video categories, supported languages, and supported regions.

Powerful, precise search filters

Narrow results the way a researcher would. Filter videos by duration (short, medium, long), definition (HD or standard), caption availability, license (including Creative Commons), livestream status (upcoming, live, or completed), location and radius, paid product placement, and more. Sort by relevance, date, rating, view count, or title, and page through large result sets with built-in pagination tokens.

Built for real workflows

Content research and planning: see what already performs in your niche before you produce.
SEO and keyword discovery: mine the titles, tags, and topics that win views.
Competitive analysis: benchmark rival channels, posting cadence, and engagement.
Influencer and creator vetting: verify reach and audience before a partnership.
Brand and media monitoring: track mentions, sentiment, and conversation around your topics.
Trend spotting: watch trending charts across regions and categories.

Public data, clean and ready to use

Every response comes back as clean, structured fields with ready-to-open YouTube links, so your agent can reason over results immediately. YouTube Discovery returns public information only. It does not download media files and does not require any private account access, which keeps it fast, safe, and simple to drop into any automation.

Frequently Asked Questions

How do I connect this tool to an external agent?

You can install the local MCP server by opening a terminal and running:

Install commands

npm install -g @agentpmt/mcp-router
agentpmt-setup

This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.

Alternatively you can connect to the hosted version with this config block, no installation required:

Hosted MCP config

{
  "mcpServers": {
    "agentpmt": {
      "type": "streamable-http",
      "url": "https://api.agentpmt.com/mcp",
      "headers": {
        "Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
        "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
      }
    }
  }
}

View MCP Connection Instructions for more details.

How does an external agent use this tool?

After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent:

Agent prompt

Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get_instructions' so you know how to use the tool search interface. Then call action 'get_schema' with tool_id 6a42b0dbb93930241f4b9932 ("YouTube Discovery"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it

The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT.

Can I filter and sort search results?

Yes. You can filter videos by date range, region, language, duration, definition, caption availability, license, livestream status, location, and category, and sort by relevance, date, rating, view count, or title.

Can it download videos or post content?

No. YouTube Discovery returns public metadata only. It does not download audio or video, and it does not create, edit, upload, or moderate content.

Can it read comments?

Yes. It lists public comment threads on a video or channel, optionally including replies, so you can analyze audience sentiment and recurring questions.

Do I need a YouTube account or API key?

No. The connection works out of the box with no account linking, API keys, or quota management on your side. Just call it and start discovering data.

How does pagination work?

Large result sets come back one page at a time with a page token. Pass that token on your next call to fetch the following page of results.

What can YouTube Discovery do?

It lets your agent search public YouTube videos, channels, and playlists, retrieve detailed video and channel statistics, find trending videos by region and category, browse playlist contents, and read public comment threads. It is a read and research tool for the public side of YouTube.

What video data can I get?

For any public video you can retrieve the title, description, channel, publish date, duration, tags, category, view count, like count, comment count, caption availability, license, and live streaming details, for up to 50 videos in a single call.

YouTube Discovery

Available ActionsEach successful request consumes credits as outlined below.

Details

Use Cases

Dynamic MCP Setup

30 Second Setup

Hosted Streamable HTTPS

Config Example

About this Product

Discover everything happening on YouTube, straight from your agent

What you can do

Powerful, precise search filters

Built for real workflows

Public data, clean and ready to use

Frequently Asked Questions

How do I connect this tool to an external agent?

How does an external agent use this tool?

Can I filter and sort search results?

Can it download videos or post content?

Can it read comments?

Do I need a YouTube account or API key?

How does pagination work?

What can YouTube Discovery do?

What video data can I get?

Related Content

YouTube Discovery, Product Announcement

Looking for help integrating AI into your business? Set up a free consultation.