Youtube Summarize

Provides access to YouTube transcripts, language selection, and optional summarization of video transcripts.

python

0

GitHub Stars

python

Language

3 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "zlatkoc-youtube-summarize": {
      "command": "uvx",
      "args": [
        "youtube-summarize"
      ]
    }
  }
}

You can run a small MCP server that fetches YouTube transcripts and optionally generates a summarized output. This server exposes tools to retrieve transcripts in multiple formats, list available languages, and produce a summarized transcript with guidance for an LLM client. It is practical for creating automated workflows that analyze video content or generate concise summaries for viewers.

How to use

You will interact with this MCP server by running it as a local or remote process and then calling its tools through an MCP client. The core capabilities let you fetch transcripts, request translations into specific languages, and optionally summarize the transcript with instructions for the LLM to produce a final summary.

What you can do with the server

Fetch transcripts in multiple formats (text, JSON, SRT, WebVTT, pretty-print)
Summarize videos by returning the transcript with summarization instructions for the LLM client
List available languages for a video's transcripts
Parse various YouTube URL forms or use a video ID
Request transcripts in specific languages with fallback priority

How to use the available tools

The server provides three primary tools through the MCP interface. Use these to perform typical tasks without building custom integrations from scratch.

get_transcript: Fetch a YouTube video's transcript in your preferred format.
summarize_transcript: Fetch a transcript and return it with summarization instructions for your LLM client.
list_transcripts: List available transcript languages for a video.

Security and data handling

Handle transcripts and video data respectfully. Do not pass along content to external services beyond what you explicitly request. If you include user-provided prompts for summarization, ensure those prompts do not reveal sensitive information unintentionally.

Notes on usage patterns

Combine the tools to build pipelines such as: fetch transcripts in your chosen language, convert to a preferred format for display, and optionally generate a concise summary for a given video.

Available tools

get_transcript

Fetch a YouTube video transcript in a chosen output format such as text, json, pretty, webvtt, or srt.

summarize_transcript

Fetch a transcript and return it together with instructions for the LLM client to produce a summary.

list_transcripts

List the available transcript languages for a given video.