{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_reggyuguvmru","handle":"mcp-youtube-intelligence-2","url":"https://wellknown.network/agents/mcp-youtube-intelligence-2","links":{"self":"https://wellknown.network/agents/mcp-youtube-intelligence-2/record.json","html":"https://wellknown.network/agents/mcp-youtube-intelligence-2","markdown":"https://wellknown.network/agents/mcp-youtube-intelligence-2/record.md","api":"https://wellknown.network/api/v1/agents/mcp-youtube-intelligence-2","status":"https://wellknown.network/api/v1/agents/mcp-youtube-intelligence-2/status","claim":"https://wellknown.network/agents/mcp-youtube-intelligence-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-youtube-intelligence-2/claim.json","badge":"https://wellknown.network/agents/mcp-youtube-intelligence-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-youtube-intelligence-2/history","tools":"https://wellknown.network/api/v1/agents/mcp-youtube-intelligence-2/tools"},"ard":{"identifier":"urn:air::server:mcp-youtube-intelligence-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-youtube-intelligence","summary":"MCP server for YouTube video intelligence — transcripts, summaries, entities, topic segmentation, and channel monitoring. Token-optimized for LLM context windows.","description":"[![Python](https://img.shields.io/badge/python-≥3.10-blue)](https://www.python.org/)\n[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)\n[![MCP](https://img.shields.io/badge/MCP-Compatible-green)](https://modelcontextprotocol.io/)\n[![PyPI](https://img.shields.io/pypi/v/mcp-youtube-intelligence)](https://pypi.org/project/mcp-youtube-intelligence/)\n\n🌐 [English](README.en.md) | **한국어**\n\n# MCP YouTube Intelligence\n\n> **YouTube 영상을 지능적으로 분석하는 [MCP](https://modelcontextprotocol.io/) 서버 + CLI**\n>\n> MCP (Model Context Protocol)는 Claude, Cursor 같은 AI 도구가 외부 서비스를 사용할 수 있게 해주는 표준 프로토콜입니다. 이 서버를 연결하면 \"이 영상 요약해줘\" 한마디로 분석이 완료됩니다.\n\n🎯 **핵심 가치**: 원본 자막(2,000~30,000 토큰)을 **서버에서 처리**하여 LLM에는 **~200–500 토큰**만 전달합니다.\n\n---\n\n## 🤔 왜 이 서버인가?\n\n대부분의 YouTube MCP 서버는 원본 자막을 그대로 LLM에 던집니다.\n\n| 기능 | 기존 MCP 서버 | MCP YouTube Intelligence |\n|------|:---:|:---:|\n| 자막 추출 | ✅ | ✅ |\n| **서버사이드 요약** (토큰 최적화) | ❌ | ✅ |\n| **구조화된 리포트** (요약+토픽+엔티티+댓글) | ❌ | ✅ |\n| **채널 모니터링** (RSS) | ❌ | ✅ |\n| **댓글 감성 분석** | ❌ | ✅ |\n| **토픽 세그멘테이션** | ❌ | ✅ |\n| **엔티티 추출** (한/영 200+개) | ❌ | ✅ |\n| **자막/YouTube 검색** | ❌ | ✅ |\n| **배치 처리** | ❌ | ✅ |\n| SQLite/PostgreSQL 캐시 | ❌ | ✅ |\n\n---\n\n## 🚀 빠른 시작\n\n### 1. 설치\n\n```bash\npip install mcp-youtube-intelligence\npip install yt-dlp  # 자막 추출에 필요\n```\n\n> 💡 LLM 없이도 기본 요약(핵심 문장 추출)은 동작합니다. 고품질 요약을 원하면 아래 [LLM 설정](#llm-프로바이더-설정)을 참고하세요.\n\n### 2. 첫 번째 명령어 실행\n\n```bash\n# 리포트 생성 — 요약, 토픽, 엔티티, 댓글을 한번에 분석\nmcp-yt report \"https://www.youtube.com/watch?v=LV6Juz0xcrY\"\n\n# 자막 요약만\nmcp-yt transcript \"https://www.youtube.com/watch?v=LV6Juz0xcrY\"\n\n# 영상 ID만 써도 됩니다\nmcp-yt report LV6Juz0xcrY\n```\n\n> ⚠️ zsh 사용자: URL에 `?`가 있으므로 반드시 **따옴표**로 감싸세요.\n\n### 📋 리포트 출력 예시\n\n`mcp-yt report LV6Juz0xcrY --no-comments` 실행 결과 (OpenClaw 활용법 영상, extractive 요약):\n\n```markdown\n# 📹 Video Analysis Report: OpenClaw Use Cases that are Actually Helpful! (ClawdBot)\n\n> Channel: Duncan Rogoff | AI Automation | Duration: 16:29 | Language: en_auto\n\n## 1. Summary\n\nOpenClaw is the most powerful AI agent framework in…","publisher":null,"homepage":"https://github.com/JangHyuckYun/mcp-youtube-intelligence","repository":"https://github.com/JangHyuckYun/mcp-youtube-intelligence","version":"0.1.3","license":null,"protocols":["mcp"],"tags":["ai","entity-extraction","llm","mcp","summarization","transcript","youtube"],"pricing":null,"endpoints":[{"url":"pypi:mcp-youtube-intelligence","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"content.writing","name":"Writing & Editing","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.825,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":0.713,"provenance":"derived"}],"categories":["content","data","documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-youtube-intelligence","registry":"pypi","observedAt":"2026-10-28T15:25:56.655Z","publishedAt":"2026-02-18T07:51:42.529928Z","latestVersion":"0.1.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-youtube-intelligence","url":"https://pypi.org/project/mcp-youtube-intelligence/","firstSeenAt":"2026-09-10T05:22:22.830Z","fetchedAt":"2026-10-28T15:24:09.398Z","normalizedAt":"2026-10-28T15:24:09.398Z"}]},"firstSeenAt":"2026-09-10T05:22:22.830Z","updatedAt":"2026-10-28T15:25:56.655Z"}