MCP / Social media

YouTube Public Data MCP

YouTube public data on the platform key: search, trending chart, statistics, channels, comments. Connect it to Claude, Codex, Cursor or any MCP client through one FlyMy.AI MCP.

Ready to use: no key10 actionsSocial media
Ask your agent
Find the most viewed YouTube videos about home espresso and give me their views and likes.

Paste it into an assistant connected to FlyMy.AI. The agent picks the actions.

What YouTube Public Data MCP can do

10 actions in the FlyMy.AI catalog, the most used first. Your agent finds them through search_tools and calls the one the task needs.

ActionWhat it does
youtube_searchKeyword search across public YouTube videos (search.list).
youtube_channel_latestLatest videos of a public YouTube channel (id, @handle or link), newest first (channels.list + playlistItems.list, 2 quota units, +1 with include_stats): full details with view count, like count...
youtube_get_channelsLook up public YouTube channels by id (UC...), @handle or channel link (channels.list, 1 quota unit per handle, ids are batched): title, handle, description, country, topics, subscriber count...
youtube_search_channelsFind creators: keyword search across public YouTube channels by topic, niche or name (search.list type=channel; uses the 100 calls per day search bucket).
youtube_trendingTrending videos: the most popular videos on YouTube right now for a country (the mostPopular chart; region_code such as US, GB, DE, BR, IN, JP), optionally narrowed to a category id (videos.list...
youtube_categoriesYouTube video category ids and names for a country (videoCategories.list, 1 quota unit) - use the ids in youtube_search and youtube_trending.
youtube_comment_repliesAll replies to one top-level YouTube comment (comments.list parentId, 1 quota unit): author, text, like count, date.
youtube_commentsPublic comment threads under a YouTube video by id or link (commentThreads.list, 1 quota unit): author, text, like count, date, reply count and optionally the first replies; order by relevance...
youtube_playlist_itemsItems of any public YouTube playlist by id or a link with list= (playlistItems.list, 1 quota unit, +1 with include_stats): full details with view count, like count, comment count, duration and topics.
youtube_statsStatistics for a batch of up to 50 YouTube video ids or links in one call (videos.list, 1 quota unit): view count, like count, comment count, duration, title, channel, date, description, tags...

Ask your agent

Requests to paste as they are. Each one runs on the actions named under it.

“Find the most viewed YouTube videos about home espresso and give me their views and likes.”uses youtube_search, youtube_stats
“What is trending on YouTube in Japan right now?”uses youtube_trending
“Show the latest videos of @mkbhd and the top comments under the newest one.”uses youtube_channel_latest, youtube_comments
“Find YouTube channels about indie game development.”uses youtube_search_channels

Connect YouTube Public Data in a minute

One MCP for every integration. Add it once, then every MCP in the catalog is a request away.

  1. 01

    Add FlyMy.AI

    Add the FlyMy.AI MCP to your assistant with one of the commands below and sign in. No key to copy.

  2. 02

    Nothing to connect

    YouTube Public Data runs on the FlyMy.AI platform key: no account and no key of yours. Calls are billed to your FlyMy.AI balance.

  3. 03

    Ask

    Paste a request from this page. Every run shows what it cost.

Claude Code
claude mcp add --transport http flymyai https://mcp-agents.flymy.ai/mcp

Then run /mcp in Claude Code and sign in.

Codex
codex mcp add flymy --url https://mcp-agents.flymy.ai/mcp

Then run codex mcp login flymy to sign in.

claude.ai and Claude Desktop
https://mcp-agents.flymy.ai/mcp

Settings, Connectors, Add custom connector: paste this URL.

Pay per run

Calls run on FlyMy.AI's key and are billed per call to your FlyMy.AI balance at the published rate. No seats and no minimum.

Go to the source

From the FlyMy.AI platform catalog of 2026-10-28: name, description, actions and setup as the platform lists them. Examples are requests to paste, not recorded runs.