collect_instagram_trend_candidates
Find public Instagram Reels for a topic within a time window.
Kabo MCP server
Kabo runs a public MCP server. Add it to an AI assistant that supports remote MCP servers, sign in once, and ask for breakout videos, account baselines and video analysis backed by public evidence.
You approve access by signing in to Kabo in your browser.
NameKabo
Server URLhttps://kabo.sh/mcp-pub
AuthenticationOAuth · sign in with Kabo
Illustrative settings screen. Labels differ by client.
One connection brings
Topic discovery Account baselines Video analysisConnect in four steps
Kabo works with clients that can add a remote MCP server over HTTP and sign in with OAuth. Menu names differ, but the steps are the same.
Open your client's MCP or connector settings and add a server with the URL https://kabo.sh/mcp-pub.
Your client opens Kabo's sign-in page in your browser. Sign in or create an account, check the access Kabo asks for, and approve it.
Mention Kabo in your request. Your assistant calls the Kabo tools it needs and answers with the evidence.
Check the sources and limits in each answer. Remove the Kabo server from your client whenever you no longer need it.
Server details
https://kabo.sh/mcp-pub
If your client uses a JSON file, the entry usually looks like this. Field names vary by client, so check its documentation.
{
"mcpServers": {
"kabo": {
"url": "https://kabo.sh/mcp-pub"
}
}
}Where it works
Add Kabo as a custom connector. The Muse page walks through it step by step.
Kabo for MuseAdd ten workflows to your existing MCP connection using Git, ZIP or npx. Compatible agents can run on your computer, in a remote workspace or in the cloud; they need Skills loading and script execution support.
Install Kabo SkillsAny assistant that supports remote MCP servers with OAuth sign-in can use the server details above.
Get the server detailsWhat the server offers
Each tool works on public evidence. Unknown numbers stay unknown, and every answer carries its sample, window and sources.
collect_instagram_trend_candidatesFind public Instagram Reels for a topic within a time window.
enrich_instagram_shortlistCompare a Reels shortlist with each account's own recent posts, so a breakout is measured against its usual reach.
collect_youtube_trend_candidatesFind public YouTube videos for a topic and publication window.
enrich_youtube_shortlistAdd exact public metrics and same-channel upload history to a YouTube shortlist.
analyze_content_videoAnalyze one public YouTube, Instagram or TikTok video. This uses your Kabo analysis allowance.
get_analysis_runRead the status, transcript and result of a video analysis you started.
The server also lists public data tools for YouTube, Instagram and TikTok: profiles, posts, comments, transcripts, search and trending sound boards.
More Kabo tools
The same evidence is on Kabo's free boards and analyzers. Open one, then bring what you find back to your assistant.
Questions, answered plainly
Yes, to connect. You sign in to Kabo in your browser when your client connects. The free tools on kabo.sh still work without an account.
Public creator evidence that Kabo collects for your request, plus the analyses and research jobs you start under your own Kabo account. Kabo cannot read other users' runs or anyone's private messages, drafts or private insights.
No. Kabo researches and analyzes. It does not publish, comment, message or edit content on any platform.
Connecting is free. Video analysis and research jobs count toward the usage included with your Kabo account, the same as in Kabo itself.
No. The server only accepts OAuth sign-in, so you never paste a Kabo key into another app.
Kabo needs a client that supports OAuth for remote MCP servers. If yours only runs local servers or only accepts API keys, use Kabo in your browser, or install the Kabo Skill in Codex or Claude Code.