Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ZeroPointRepo/youtube-mcp --skill youtubegit clone --depth 1 https://github.com/ZeroPointRepo/youtube-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zeropointrepo/youtube-mcp/youtube)<a href="https://agentmods.dev/skills/zeropointrepo/youtube-mcp/youtube"><img src="https://agentmods.dev/badge/skills/zeropointrepo/youtube-mcp/youtube/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zeropointrepo/youtube-mcp/youtube"><img src="https://agentmods.dev/badge/skills/zeropointrepo/youtube-mcp/youtube.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.01103 |
| Opus 5 | $0.00044 | $0.00551 |
| Sonnet 5 | $0.00017 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
youtube scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube (TranscriptAPI)
This plugin bundles the hosted transcriptapi MCP server (https://transcriptapi.com/mcp). Its six tools are the only data path — never scrape youtube.com and never call the REST API directly from this skill.
Authentication is automatic. The MCP server uses OAuth: the first tool call prompts the user to sign in (or create a free account — 100 credits, no card). There is no API key to configure. If tools fail with an auth error, tell the user to complete the sign-in prompt in their client, or re-enable the transcriptapi MCP server in settings.
When to use
DO use when the user:
- Pastes a YouTube link or 11-character video ID, or asks to summarize, quote, transcribe, translate or fact-check a video →
get_youtube_transcript - Asks what a video says, or wants the spoken content — even without saying "transcript" →
get_youtube_transcript - Wants to find videos or channels on a topic →
search_youtube - Names a creator, pastes an
@handleor channel URL, or asks what a channel posted recently →get_channel_latest_videos(free) - Wants to search within a channel →
search_channel_videos - Wants a channel's full upload history →
list_channel_videos - Pastes a playlist link, or wants every video in a series or course →
list_playlist_videos - Is researching a topic where talks, lectures, tutorials or reviews are good sources →
search_youtube, then transcripts of the best hits
Do NOT use when:
- A YouTube link appears incidentally (an email signature, an unrelated citation)
- The user is discussing YouTube as a platform rather than asking about specific content
- The user wants to upload, comment, or manage an account — this plugin is read-only
Tools (exact MCP surface)
get_youtube_transcript — 1 credit
video_url(string, required): full URL (youtube.com/watch?v=ID), short URL (youtu.be/ID), shorts URL, or a bare 11-character video ID.format(string, default"text"):"text"for markdown,"json"for per-segment objects withstartandduration.include_timestamp(boolean, defaulttrue),send_metadata(boolean, defaulttrue) — metadata adds title, author and thumbnail.- Use
format="json"only when you need to cite or seek to exact timestamps;"text"is cheaper to reason over.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 73 lines · 87 tokens per session scan A 7adbb7e760c0
youtube is a skill published in the GitHub repository ZeroPointRepo/youtube-mcp (10 stars, last pushed 17d ago), licensed MIT. It adds 87 tokens to every session and 1,103 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
youtube-full
Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, first looks, or…
captions
Use when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to read, quote, or translate a video, accessibility needs, deaf/HoH use cases, content review, or language learning. Fetches timestamped caption data from any YouTube…
video-transcript
Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content. Also use when a user shares a video URL without explanation and wants to know what it says. Not for uploads or…
youtube
Complete YouTube toolkit: transcripts, captions and subtitles, video and channel search, channel browsing, within-channel search, playlist extraction and new-upload monitoring, powered by TranscriptAPI. Use whenever YouTube is or could be relevant, even if not explicitly mentioned: pasted video, channel or playlist…
youtube
Working knowledge of the bundled TranscriptOut MCP server. Reach for it whenever a task touches YouTube, said or unsaid: a pasted video, channel or playlist link, a bare video ID or @handle, a talk to summarize, quote, translate or fact-check, research that runs through lectures and reviews, or a creator to keep up…
post-to-xhs
A publishing guide for 小红书, a Chinese social-media platform. It covers posting image-and-text content or a longer formatted article, using supplied content or a webpage.