di37/youtube-video-analysis-toolkit

이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기

23 stars 8 forks 품질 53 트렌드 11MIT

AI-powered YouTube video analysis toolkit using MCP. Extract transcripts, generate knowledge graphs, generate high-quality detailed notes, perform sentiment analysis, and topic modeling through an...

개요

A comprehensive toolkit for analyzing YouTube videos using AI-powered analysis capabilities. This project provides transcript extraction, knowledge graph generation, sentiment analysis, topic modeling, and note generation for educational and research purposes. Interface of MCP Powered YouTube Video Analysis Toolkit. Extract and analyze transcripts from YouTube videos. Interactive knowledge graphs from video content. Automated markdown note generation from transcripts. Comprehensive sentiment analysis with emotional breakdowns. Content classification and structure analysis. - Standardized tool access across multiple AI providers - Multi-server support for distributed analysis capabilities - Asynchronous streaming for real-time agent interactions The project consists of two main components:

README

원문 README의 일부입니다. 원문 보기.

MCP-Powered YouTube Video Analysis Toolkit

Features

YouTube Video Analysis - Chat Interface

Interface of MCP Powered YouTube Video Analysis Toolkit. Extract and analyze transcripts from YouTube videos.

Knowledge Graph Generation

Interactive knowledge graphs from video content.

High Quality Note Generation

Automated markdown note generation from transcripts.

Sentiment Analysis

Comprehensive sentiment analysis with emotional breakdowns.

Topic Modeling

Content classification and structure analysis.

MCP Integration: Model Context Protocol for seamless AI agent integration

Standardized tool access across multiple AI providers
Multi-server support for distributed analysis capabilities
Asynchronous streaming for real-time agent interactions

Architecture

The project consists of two main components:

Server (`/server`)

FastMCP Server: Built with FastMCP 2.0 framework for Model Context Protocol implementation
- Automatic tool discovery and async support for high-performance operations
- Pythonic decorators for simple function-to-tool conversion
- Built-in authentication and proxying capabilities
- Comprehensive protocol handling with minimal boilerplate code
YouTube Tools: Video transcript extraction and search capabilities via MCP tools
Analysis Tools: AI-powered prompts exposed as MCP resources for knowledge graphs, sentiment analysis, and topic modeling
Data Storage: Persistent storage management for transcripts, notes, and analysis results

Client (`/client`)

MCP Client Integration: Built with mcp-use library for seamless MCP server communication
- Multi-server support enabling connection to multiple MCP servers simultaneously
- Asynchronous streaming of agent outputs for real-time interactions
- Dynamic server selection for optimized task execution
- Configurable via JSON for flexible server management
Streamlit Dashboard: Interactive web interface for visualization
Multi-tab Interface: Separate views for different analysis types
Real-time Chat: MCP-powered chatbot for video analysis using intelligent agents
Data Visualization: Interactive charts and graphs for analysis results

Project Structure

youtube-video-analysis-kit/
├── README.md
├── data/                          # Shared data directory
│   ├── transcripts/              # YouTube video transcripts

GitHub에서 전체 README 보기

설치

This server does not publish a one-line install command.

Open the repository installation guide MCP 초보자라면? mcpskill.org 가이드부터 시작하세요 →

설정

{
    "mcpServers": {
        "video-analysis-kit": {
            "url": "http://{your_ip_address}:8000/mcp",
            "transport": "streamable-http"
        }
    }
}