Docs menu
Get started
What is Opus GrowthQuickstartAdd to your AIHow it worksSafety and approvalCreditsPlansFAQAI apps
All AI appsChatGPTClaudeGrokPerplexityClaude CodeCodexGemini CLIOpenClawCursorVS CodeWindsurfOther MCPConnect ad platforms
Google AdsMeta AdsLinkedIn AdsMicrosoft AdvertisingTikTok AdsChatGPT AdsAgencies and MCCConnect data sources
Search ConsoleGoogle AnalyticsYouTubeBusiness ProfileTag ManagerWebsites and SEO
AI ServerWordPressSEO IntelligenceClick fraudTool reference
All toolsGoogle AdsMeta AdsTikTok AdsLinkedIn AdsMicrosoft AdvertisingChatGPT AdsSearch ConsoleGoogle AnalyticsYouTubeBusiness ProfileTag ManagerWordPressAI ServerSEO IntelligenceClick fraudCross-channelAccount and billingLanguage
YouTube Top Videos
MOST-WATCHED videos (last N days): title + views + watch time (min) + avg.
- Type
- Reads only
- Credits
- 2
- Platform
- YouTube
- Approval
- Not needed, nothing changes
What it does
MOST-WATCHED videos (last N days): title + views + watch time (min) + avg. view duration (sec). channel = from youtube_channels (leave empty if there is only one channel). Every matching video is retained: ``limit`` only controls this response page (0 = as many as safely fit), and ``page_token=next_page_token`` retrieves the cached remainder without another YouTube request or credit. The default remains 10 for compatibility.
MCP: youtube_top_videos
How to use it
You don't call tools by name. Write what you want in ChatGPT, Claude or another assistant connected to Opus Growth, in your own words; it picks this tool when it fits.
Parameters
| Name | Type | Required | Default | |
|---|---|---|---|---|
| channel | string | Optional | · | Channel identifier or channel selector returned by the relevant YouTube/channel-listing operation. |
| days | integer | Optional | 28 | Number of calendar days to look back from now for this analysis or report. |
| limit | integer | Optional | 10 | Maximum number of rows returned in this response. When the result has_more flag is true, continue with next_page_token rather than assuming the list is complete. |
| page_token | string | Optional | · | Continuation token returned as next_page_token by a previous call. Leave empty for the first page; pass it unchanged to retrieve the cached next page. |