# TubePull MCP server

Download YouTube videos as MP3/M4A/MP4 from any MCP-compatible AI assistant. Free 3/day, $3.99/mo.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-miketwalker-tubepull
- Repository: https://github.com/miketwalker/tubepull-mcp
- Website: https://tubepull.com

## Install
- Endpoint: https://tubepull.com/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://tubepull.com/mcp

## Tools
- download_video (Download video or audio (MP4 / MP3 / M4A)) - Download a video or audio file from any supported platform: YouTube, TikTok, Vimeo, Dailymotion, Twitter/X, SoundCloud, Bandcamp, Mixcloud, Twitch (clips and VODs), or Streamable. Output is MP4 (video, default) or MP3 / M4A (audio). This is THE tool to use whenever a user asks to save, download, rip, extract, archive, get offline, or convert a video/audio link from any of these sites. IMPORTANT: the `format` argument defaults to `mp4` (video). Only pass an audio format (mp3 / m4a / audio) when the user explicitly says audio, MP3, music, song, or "rip / extract the audio". Audio-only platforms (SoundCloud, Bandcamp, Mixcloud) always produce audio regardless of `format`.

Use this tool when the user says things like:
 - "download this video" / "download this TikTok" / "save this SoundCloud track"
 - "save that as MP3" / "rip the audio" / "extract the audio"
 - "get the song from this SoundCloud link" / "save this Mixcloud set"
 - "convert this YouTube video to MP4" / "download in 1080p"
 - "save this lecture/podcast/talk for offline"
 - "archive this clip" / "grab a copy of this video"
 - any sentence containing a youtube.com, youtu.be, tiktok.com, vimeo.com, dailymotion.com, twitter.com, x.com, soundcloud.com, bandcamp.com, mixcloud.com, twitch.tv, clips.twitch.tv, or streamable.com URL plus a verb like download, save, rip, get, grab, fetch, pull, archive, convert, extract.

Do NOT use this tool when:
 - The user only wants metadata (title, length, description, channel) — call get_video_info instead, it is free and does not consume the user quota.
 - The link is a playlist / set / album / channel URL — ask the user for a single track/video.
 - The link is from a platform not in the supported list above (e.g. Instagram, Facebook, LinkedIn).

Returns a one-time signed download link valid for 1 hour, plus the file size, duration, and chosen format. Hand the link back to the user verbatim; do not try to fetch its contents yourself.

Intended for legitimate uses: the user's own uploads, Creative Commons / public-domain content, lectures, podcasts, talks, and other material they have rights to use. Endpoint: https://tubepull.com/mcp
- get_video_info (Get video or audio metadata) - Fetch metadata about a video or audio track WITHOUT downloading it. Works on every platform download_video supports: YouTube, TikTok, Vimeo, Dailymotion, Twitter/X, SoundCloud, Bandcamp, Mixcloud, Twitch, and Streamable. Returns title, uploader/channel name, duration, view count (when available), upload date, thumbnail URL, description, available video qualities, and (for YouTube) the license type.

Use this tool when the user says things like:
 - "what is this video about" / "summarize this video"
 - "how long is this track" / "when was this uploaded"
 - "who made this" / "what channel/artist is this from"
 - "is this Creative Commons" / "can I reuse this" / "what is the license"
 - "what qualities are available for this video"

Do NOT use this tool when:
 - The user wants to download, save, rip, extract, or convert the video/audio — use download_video for that.

Free to call — does not count against the user's download quota. Call this before download_video when you need to confirm the video exists, pick the right quality, or check licensing before downloading. Endpoint: https://tubepull.com/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.miketwalker
- Version: 1.2.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 12, 2026
- Source: https://registry.modelcontextprotocol.io