Skip to main content
Glama

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

video_info(url)

Title, channel, duration, chapters

list_transcripts(url)

Caption languages available

get_transcript(url, start?, end?, languages?)

YouTube captions with timestamps. Fast, no GPU

transcribe(url, start?, end?, model?, language?)

Downloads audio (only the slice you ask for) and runs Whisper locally

screenshots(url, times, max_height?)

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 ffmpeg
git clone https://github.com/zoukkis/youtube-listen-mcp
cd youtube-listen-mcp
uv sync --extra whisper     # drop --extra whisper if you only want captions

Test it with the MCP inspector:

npx @modelcontextprotocol/inspector uv run youtube-listen-mcp

GPU (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=float16
  • No NVIDIA GPU, or on macOS: use WHISPER_DEVICE=cpu WHISPER_COMPUTE_TYPE=int8. The small model 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. Run uv sync --extra whisper.

  • open() got an unexpected keyword argument 'metadata_errors': PyAV 19 or later is installed. The extra pins av<19, so running uv sync --extra whisper again 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

WHISPER_MODEL

small

tiny / base / small / medium / large-v3

WHISPER_DEVICE

auto

cuda or cpu

WHISPER_COMPUTE_TYPE

default

float16 on modern NVIDIA cards; int8 or float32 on Pascal (e.g. Tesla P40) or CPU

Notes

  • This gives the model text, not sound, so it gets the speech but not tone, music or other sounds. screenshots adds still frames, not motion.

  • YouTube sometimes rate-limits or blocks caption requests, especially from cloud IPs. If that happens, transcribe is the fallback.

  • Respect YouTube's Terms of Service and creators' rights when downloading audio.

License

MIT

Available Tools

5 tools
get_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

    A3.8/5.0

    Scored across 5 tools

    Disambiguation4/5

    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 Consistency3/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers