mcp-idea-capture
mcp-idea-capture
An MCP server that takes a video URL and gives you back a transcript plus a short "here's the actual idea" summary. It's for the case where you see something useful in a reel or a talk and don't want to sit and type it out.
It pulls the audio with yt-dlp, transcribes it with Groq's Whisper API, and runs the transcript through an LLM (Gemini by default) to pull out the point. yt-dlp supports a lot of sites, not just one. Nothing is saved until you decide it's worth keeping.
Tools
tool | what it does |
| download audio, transcribe, extract the idea. Returns everything; saves nothing. |
| append an |
Private or login-gated videos come back with a plain message instead of a crash.
Setup
git clone https://github.com/<you>/mcp-idea-capture
cd mcp-idea-capture
python -m venv .venv && . .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # add your keys
python test_client.py # lists the tools
python test_client.py "https://www.youtube.com/shorts/XXXX" # runs the pipelineKeys (put them in .env or the environment):
GROQ_API_KEY- transcription. Free tier at console.groq.com, no card.GEMINI_API_KEY- idea extraction. Free tier at aistudio.google.com.GOOGLE_API_KEYworks as an alias.
Optional: IDEAS_FILE, WHISPER_MODEL (default whisper-large-v3),
GEMINI_MODEL (default gemini-3.5-flash).
Adding it to an MCP client
~/.claude.json or claude_desktop_config.json:
{
"mcpServers": {
"idea-capture": {
"command": "/abs/path/mcp-idea-capture/.venv/bin/python",
"args": ["/abs/path/mcp-idea-capture/server.py"]
}
}
}Notes
Audio only. It never downloads or stores the video, just the audio, long enough to transcribe, then the temp folder is deleted.
Groq caps uploads around 25 MB, so very long videos will be rejected. Clip them first.
The idea-extraction prompt is short and opinionated on purpose (give the point, don't retell). Edit
_extract_ideainserver.pyif you want a different style.
License
MIT.