search_videosLABSCO SUMMARY
Research across videos, not just inside one.
The enhanced transcript tool is what separates it: several videos at once, filtered to a time range or a keyword, with timestamps and metadata — which turns "what did these five talks say about X" into one call instead of five transcript reads.
What it is
A fuller YouTube toolkit built on the Data API: searching with real filters, channel and video detail, comments with sorting, related and trending video lists, plus a transcript layer that goes beyond fetching text — filtering, searching and multi-video extraction.
What you get
- Videos —
search_videoswith filtering by channel, duration and region,get_video_detailsfor title, channel, views and likes,get_video_commentswith sorting,get_related_videos,get_trending_videosby region - Channels —
get_channel_detailsfor name, subscribers and views - Transcripts —
get_video_transcriptin the languages you name, andget_video_enhanced_transcriptfor filtering, keyword search, time-bounded slices, timestamped output and several videos at once transcript_summary— a prompt that summarises a video from its transcript with options you set- Resources addressed by URI:
youtube://video/{video_id},youtube://channel/{channel_id},youtube://transcript/{video_id}?language={language}, andyoutube://available-youtube-toolsfor the tool list itself
Requirements
Python 3.12 or higher and a YouTube API key: create a Google Cloud project, enable the YouTube Data API v3, create an API key, and put it in YOUTUBE_API_KEY. Install with uv into a 3.12 virtual environment, or build the Docker image and pass the key as an environment variable; Smithery installs it into Claude Desktop in one command. Because search, comments and trending all go through the Data API, they draw on that key's quota — the transcript tools are the ones that keep working when it runs out.
Setup effort
One command plus a key — npx -y @smithery/cli install @jikime/py-mcp-youtube-toolbox --client claude, then supply credentials
USE CASES
01
Finding the right video before reading it
Search with channel, duration and region filters, check the details, then pull the transcript of the one that fits.
02
Comparing what several videos said about a topic
Run the enhanced transcript across multiple video IDs with a keyword query, so the relevant passages surface together.
03
Reading the room around a video
Pull the comments with a sort order to see what the audience actually argued about.
04
Seeing what is landing right now
Get the trending list for a region, then check the channel behind whatever stands out.
05
Quoting a specific moment
Ask for timestamped output over a time range so the quote comes with the point in the video it came from.
06
Following a thread of related material
Walk from one video to its related ones, and pull transcripts as you go.
8 tools
Listed in project docs. Your client may show a different list.
get_video_detailsget_video_commentsget_related_videosget_trending_videosget_channel_detailsget_video_transcriptget_video_enhanced_transcriptBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
- uv and Python 3.12+ for the uv tabs — or docker on PATH for the Docker tab
- YOUTUBE_API_KEY — a YouTube Data API v3 key from Google Cloud Console
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @smithery/cli install @jikime/py-mcp-youtube-toolbox --client claudeMCP Clients
Claude Desktop — uv, Cursor — uv
TERMINAL
git clone https://github.com/jikime/py-mcp-youtube-toolbox.git
cd py-mcp-youtube-toolbox
curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv -p 3.12
uv pip install -r requirements.txtJSON
{
"mcpServers": {
"YouTube Toolbox": {
"command": "<YOUR_PATH_TO_BIN_UV>",
"args": [
"--directory",
"<YOUR_PATH_TO_PY_MCP_YOUTUBE_TOOLBOX>",
"run",
"server.py"
],
"env": {
"YOUTUBE_API_KEY": "<YOUR_YOUTUBE_API_KEY>"
}
}
}
}<YOUR_PATH_TO_BIN_UV> is the full path of your uv binary (which uv prints it), and <YOUR_PATH_TO_PY_MCP_YOUTUBE_TOOLBOX> is the full path of your clone, and <YOUR_YOUTUBE_API_KEY> is your YouTube Data API v3 key.
Claude Desktop — Docker
CLAUDE DESKTOP — DOCKER · TERMINAL
git clone https://github.com/jikime/py-mcp-youtube-toolbox.git
cd py-mcp-youtube-toolbox
docker build -t py-mcp-youtube-toolbox .CLAUDE DESKTOP — DOCKER · JSON
{
"mcpServers": {
"YouTube Toolbox": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"YOUTUBE_API_KEY=<YOUR_YOUTUBE_API_KEY>",
"py-mcp-youtube-toolbox"
]
}
}
}The image is built locally by the docker build step; <YOUR_YOUTUBE_API_KEY> is a YouTube Data API v3 key.
