# As a condition of accessing this website, you agree to abide by the following # content signals: # (a) If a Content-Signal = yes, you may collect content for the corresponding # use. # (b) If a Content-Signal = no, you may not collect content for the # corresponding use. # (c) If the website operator does not include a Content-Signal for a # corresponding use, the website operator neither grants nor restricts # permission via Content-Signal with respect to the corresponding use. # The content signals and their meanings are: # search: building a search index and providing search results (e.g., returning # hyperlinks and short excerpts from your website's contents). Search does not # include providing AI-generated search summaries. # ai-input: inputting content into one or more AI models (e.g., retrieval # augmented generation, grounding, or other real-time taking of content for # generative AI search answers). # ai-train: training or fine-tuning AI models. # ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF # RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT # AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET. # BEGIN Cloudflare Managed content User-agent: * Content-Signal: search=yes,ai-train=no Allow: / User-agent: Amazonbot Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: CloudflareBrowserRenderingCrawler Disallow: / User-agent: Google-Extended Disallow: / User-agent: GPTBot Disallow: / User-agent: meta-externalagent Disallow: / # END Cloudflare Managed Content TubeMCP — YouTube transcripts for AI agents
TubeMCP

YouTube transcripts for your AI agent.

Search videos, fetch transcripts. Two MCP tools, zero config.

Give your agent YouTube.

TubeMCP is an open-source MCP server that lets your AI agent search YouTube and fetch transcripts. Search by topic to find relevant videos, then pull the full transcript, title, channel, duration, and publish date. Results are cached locally in SQLite so repeated requests are instant.

Summarize this talk and pull out every library and tool they mention: https://www.youtube.com/watch?v=Cf6CHpLbf5w
Here are three talks on async Python — compare their approaches and tell me which patterns overlap: https://www.youtube.com/watch?v=Qb9s3UiMSTA, https://www.youtube.com/watch?v=K56nNuBEd0c, https://www.youtube.com/watch?v=3E-Ym2mbSCc
Find recent videos on building MCP servers and write me a step-by-step getting-started guide based on what they cover.

Install

Two steps — install the package, then add it to your client.

1. Install 
pip install tubemcp

or

uv tool install tubemcp
2. Add to your client 
claude mcp add tubemcp -- tubemcp

Requires Python 3.10+

Two tools, zero config

TubeMCP gives your agent two tools — search for videos and pull transcripts.

youtube_search

Find videos by topic. Pass one or more queries, get back metadata.

[
  {
    "video_id": "Cf6CHpLbf5w",
    "title": "Building MCP Servers in Python",
    "url": "https://www.youtube.com/watch?v=Cf6CHpLbf5w",
    "duration_seconds": 1423,
    "channel_name": "Tech Talk"
  }
]
youtube_get_transcript

Get the full transcript and metadata for a video. Accepts any YouTube URL or video ID.

{
  "video_id": "Cf6CHpLbf5w",
  "title": "Building MCP Servers in Python",
  "channel_name": "Tech Talk",
  "thumbnail_url": "https://i.ytimg.com/vi/Cf6CHpLbf5w/hq720.jpg",
  "duration_seconds": 1423,
  "publish_date": "2025-01-15",
  "transcript": [
    { "text": "Welcome to the talk.", "start": 0.0, "duration": 2.5 },
    { "text": "Today we're building MCP servers.", "start": 2.5, "duration": 3.1 }
  ],
  "from_cache": false
}

Transcripts are cached locally in ~/.tubemcp/cache.db — repeated requests are instant.