youtube-listen-mcp
Enables AI assistants to "listen" to YouTube videos: fetch video info (title, channel, duration, chapters), list available caption languages, retrieve timestamped captions, transcribe audio locally with Whisper, and capture still frames at specific timestamps. Caption retrieval and transcription can be limited to a specific time range, and screenshots can be requested for up to 10 timestamps at a chosen resolution.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@youtube-listen-mcp what does the speaker say between 12:00 and 15:30 in https://youtu.be/dQw4w9WgXcQ"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
youtube-listen-mcp
An MCP server that lets AI assistants like Claude "listen" to YouTube videos. It can read a video's captions, or transcribe the audio locally with Whisper, and either one can be limited to a specific time slot.
Tools
Tool | What it does |
| Title, channel, duration, chapters |
| Caption languages available |
| YouTube captions with timestamps. Fast, no GPU |
| Downloads audio (only the slice you ask for) and runs Whisper locally |
| Frames at the given timestamps (up to 10), returned as images the model can see. Only those frames are fetched, not the whole video. Up to 720p by default |
Times can be given as 90, 1:30, 01:02:03 or 1h2m3s.
Related MCP server: ytmcp
Install
Requirements: Python 3.10+, uv, and ffmpeg for transcribe and screenshots:
sudo apt install ffmpeggit clone https://github.com/zoukkis/youtube-listen-mcp
cd youtube-listen-mcp
uv sync --extra whisper # drop --extra whisper if you only want captionsTest it with the MCP inspector:
npx @modelcontextprotocol/inspector uv run youtube-listen-mcpGPU (NVIDIA)
On Linux, --extra whisper also installs NVIDIA's CUDA 12 cuBLAS and cuDNN 9 libraries from PyPI (about 1 GB), and the server loads them automatically. You don't need a system-wide CUDA toolkit, sudo or LD_LIBRARY_PATH. You only need an NVIDIA driver that supports CUDA 12 or later; nvidia-smi shows the version in its top right corner.
To force the GPU and use half precision, set:
WHISPER_DEVICE=cuda WHISPER_COMPUTE_TYPE=float16No NVIDIA GPU, or on macOS: use
WHISPER_DEVICE=cpu WHISPER_COMPUTE_TYPE=int8. Thesmallmodel is fine on CPU for short clips.Windows: the bundled libraries are Linux only. Install CUDA 12 cuBLAS and cuDNN 9 yourself and put them on
PATH, or use CPU.Library libcublas.so.12 is not found: the extra isn't installed. Runuv sync --extra whisper.open() got an unexpected keyword argument 'metadata_errors': PyAV 19 or later is installed. The extra pinsav<19, so runninguv sync --extra whisperagain fixes it.
Use with Claude
Claude Code
claude mcp add -s user youtube-listen -- uv --directory /path/to/youtube-listen-mcp run youtube-listen-mcp-s user makes it available in every project. Add -e WHISPER_DEVICE=cuda -e WHISPER_COMPUTE_TYPE=float16 before -- to use the GPU.
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"youtube-listen": {
"command": "uv",
"args": ["--directory", "/path/to/youtube-listen-mcp", "run", "youtube-listen-mcp"],
"env": { "WHISPER_MODEL": "large-v3" }
}
}
}Or run it straight from GitHub without cloning:
"args": ["--from", "youtube-listen-mcp[whisper] @ git+https://github.com/zoukkis/youtube-listen-mcp", "youtube-listen-mcp"]with "command": "uvx".
Then ask: "What does the speaker say between 12:00 and 15:30 in https://youtu.be/…?"
Or combine speech and visuals: "In https://youtu.be/…, transcribe 19:12–21:22 and look at the screen at 17:11 and 19:21. What's being shown and explained?"
Configuration
Env var | Default | Notes |
|
|
|
|
|
|
|
|
|
Notes
This gives the model text, not sound, so it gets the speech but not tone, music or other sounds.
screenshotsadds still frames, not motion.YouTube sometimes rate-limits or blocks caption requests, especially from cloud IPs. If that happens,
transcribeis the fallback.Respect YouTube's Terms of Service and creators' rights when downloading audio.
License
MIT
Available Tools
5 toolsget_transcriptA
Fetch a video's YouTube captions with timestamps.
Args: url: YouTube URL or video ID. start: Optional start of the time slot, e.g. "12:30", "750", "12m30s". end: Optional end of the time slot. languages: Preferred language codes in order, default ["en"].
Fast and needs no GPU. If the video has no captions, use transcribe.
Inputs: url (required), end, start, languages. Returns: result
list_transcriptsB
List the caption tracks (languages, manual vs auto-generated) a video has.
Inputs: url (required). Returns: result
screenshotsA
Grab still frames from a YouTube video at the given timestamps.
Use this to see what is on screen (slides, code, diagrams, people) at
specific moments. Combine with get_transcript or transcribe for the
surrounding speech. Only the frames are fetched, not the whole video.
Args: url: YouTube URL or video ID. times: Timestamps to capture, e.g. ["17:11", "19:21"]. Max 10. max_height: Maximum frame height in pixels (default 720).
Inputs: url (required), times (required), max_height.
transcribeA
Download the audio and transcribe it locally with Whisper.
Slower than get_transcript but works when there are no captions and is
usually more accurate. Pass start/end to download only that slice.
Args: url: YouTube URL or video ID. start: Optional start of the time slot, e.g. "12:30". end: Optional end of the time slot. model: Whisper model (tiny, base, small, medium, large-v3). Defaults to $WHISPER_MODEL or "small". language: Optional language code, e.g. "en", "fi". Auto-detect if empty.
Inputs: url (required), end, model, start, +1 more. Returns: result
video_infoB
Get a YouTube video's title, channel, duration and chapter list.
Useful for finding the time slot to read before fetching a transcript.
Inputs: url (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: metadata, caption listing, caption fetching, local transcription, and frame capture. The closest pair is list_transcripts vs get_transcript, but the descriptions make the list-vs-fetch distinction clear.
Naming mixes conventions: 'screenshots' (noun plural), 'video_info' (noun phrase), 'list_transcripts'/'get_transcript' (verb_noun), and 'transcribe' (bare verb). It is readable but not a predictable pattern.
Five tools is well-scoped for the domain, with no redundant entries. Each tool earns its place in the metadata-to-transcript-to-transcription workflow.
The surface covers video info, transcript discovery, caption fetching, fallback transcription, and visual capture. A transcript-search/lookup helper would be a nice addition, but agents can work around it using timestamps.
Maintenance
Related MCP Connectors
YouTube for AI agents: transcripts, comments, video stats, channel monitor, Shorts captions.
Extract YouTube transcripts, search what was said, and read on-screen frames with cited timestamps.
Search YouTube videos, read transcripts and get public video information in your AI assistant.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to watch YouTube videos by extracting frames at scene changes and visual references, pairing each frame with the exact words spoken at that timestamp. Provides dense frame-transcript interleaving for any model.6MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to fetch YouTube video transcripts with precise timestamps, multi-language support, and time-range filtering.31MIT
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with YouTube videos by fetching transcripts, summarizing content, and answering questions based on video context.-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to extract educational content from YouTube videos by fetching timestamped transcripts and visually meaningful frames, returning them as base64 JPEGs for analysis.-