YouTube transcript extractor for your LLM
LocalAbout YouTube transcript extractor for your LLM
YouTube transcript extractor for your LLM is an MCP server that retrieves transcripts from YouTube videos for use with an LLM. It supports transcript summarization and extraction of noteworthy information through prompts.
Key features
- 01Download YouTube video transcripts
- 02Make transcripts available to an LLM
- 03Summarize transcript content
- 04Highlight new information
Use cases
- 01Summarize a YouTube video transcript
- 02Find notable information in a video
- 03Provide video transcript text to an LLM
MCP support
Uses MCP to make downloaded YouTube transcripts available to an LLM.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEYouTube transcript extractor for your LLM
This project will download the transcript for a YouTube video, and make it avaiable to your LLM. It does this via the MCP protocol.
Installation
Use
Use a prompt in the following format:
To download a transcript
Download the transcript for https://www.youtube.com/watch?v=QGzgsSXdPjo. Use the MCP server.
To get a summary
Summarize the transcript
To extract new and interesting information from the transcript. This prompt often reveals very interesting information:
highlight new information from the transcript
Motivation
I build this service to better understand how MCP servers work. It has also allowed me to explore how to build software with LLMs (in this case Claude).
I've captured the (important) prompts that I used when building the server.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.