A public MCP server that pulls the full subtitles out of a YouTube video, so an AI assistant can read a whole lecture instead of guessing from the title.
https://mcp-youtube.lyabah.com/mcp
No API key, no account, no setup. Point any MCP client at that URL and ask it about a YouTube video.
Settings → Connectors → Add custom connector, then paste the endpoint URL above.
claude mcp add --transport http youtube https://mcp-youtube.lyabah.com/mcp
The server speaks MCP over streamable HTTP:
{
"mcpServers": {
"youtube": {
"type": "http",
"url": "https://mcp-youtube.lyabah.com/mcp"
}
}
}
Returns the subtitles of a video as text. By default you get the whole thing — a two-hour lecture comes back as one document.
| Parameter | Meaning |
|---|---|
url | Any YouTube link — watch, youtu.be, shorts, embed, live — or a bare video ID. Required. |
lang | Preferred subtitle language, e.g. en, uk. Defaults to the video's own. |
translate_to | Machine-translate the subtitles into this language. |
format | text (default), timestamped, or srt. |
max_chars | Cap the response size. 0 (default) returns everything. |
offset_chars | Continue where a capped response stopped. |
Lists which subtitle languages a video offers, whether each was written by a human or generated by speech recognition, and which languages it can be translated into.
Just paste a link and ask:
Summarise https://www.youtube.com/watch?v=... for me
What does this video say about X?
Pull the exact quote where they talk about Y