Integrates with Google Gemini models to provide AI-powered video reporting and summarization.
Enables local, offline video analysis and summarization by connecting to Ollama instances running various LLMs.
Integrates with OpenAI models like GPT-4o-mini for intelligent video summarization and content processing.
Supports using PostgreSQL as a persistent database backend for caching and searching video data.
Allows for monitoring YouTube channels for new content updates through integrated RSS feed tracking.
Provides local storage and caching for video metadata, transcripts, and analysis results to optimize performance.
Enables searching for videos, fetching metadata, extracting transcripts, analyzing comments, and processing playlists to provide comprehensive video intelligence.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP YouTube IntelligenceSummarize this video and analyze the viewer sentiment: https://youtu.be/LV6Juz0xcrY"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π English | νκ΅μ΄
MCP YouTube Intelligence
YouTube μμμ μ§λ₯μ μΌλ‘ λΆμνλ
MCP (Model Context Protocol)λ Claude, Cursor κ°μ AI λκ΅¬κ° μΈλΆ μλΉμ€λ₯Ό μ¬μ©ν μ μκ² ν΄μ£Όλ νμ€ νλ‘ν μ½μ λλ€. μ΄ μλ²λ₯Ό μ°κ²°νλ©΄ "μ΄ μμ μμ½ν΄μ€" νλ§λλ‘ λΆμμ΄ μλ£λ©λλ€.
π― ν΅μ¬ κ°μΉ: μλ³Έ μλ§(2,000~30,000 ν ν°)μ μλ²μμ μ²λ¦¬νμ¬ LLMμλ ~200β500 ν ν°λ§ μ λ¬ν©λλ€.
π€ μ μ΄ μλ²μΈκ°?
λλΆλΆμ YouTube MCP μλ²λ μλ³Έ μλ§μ κ·Έλλ‘ LLMμ λμ§λλ€.
κΈ°λ₯ | κΈ°μ‘΄ MCP μλ² | MCP YouTube Intelligence |
μλ§ μΆμΆ | β | β |
μλ²μ¬μ΄λ μμ½ (ν ν° μ΅μ ν) | β | β |
ꡬ쑰νλ 리ν¬νΈ (μμ½+ν ν½+μν°ν°+λκΈ) | β | β |
μ±λ λͺ¨λν°λ§ (RSS) | β | β |
λκΈ κ°μ± λΆμ | β | β |
ν ν½ μΈκ·Έλ©ν μ΄μ | β | β |
μν°ν° μΆμΆ (ν/μ 200+κ°) | β | β |
μλ§/YouTube κ²μ | β | β |
λ°°μΉ μ²λ¦¬ | β | β |
SQLite/PostgreSQL μΊμ | β | β |
π λΉ λ₯Έ μμ
1. μ€μΉ
pip install mcp-youtube-intelligence
pip install yt-dlp # μλ§ μΆμΆμ νμπ‘ LLM μμ΄λ κΈ°λ³Έ μμ½(ν΅μ¬ λ¬Έμ₯ μΆμΆ)μ λμν©λλ€. κ³ νμ§ μμ½μ μνλ©΄ μλ LLM μ€μ μ μ°Έκ³ νμΈμ.
2. 첫 λ²μ§Έ λͺ λ Ήμ΄ μ€ν
# 리ν¬νΈ μμ± β μμ½, ν ν½, μν°ν°, λκΈμ νλ²μ λΆμ (LLM μ°λνμ)
mcp-yt report "https://www.youtube.com/watch?v=LV6Juz0xcrY"
# μλ§ μμ½λ§
mcp-yt transcript "https://www.youtube.com/watch?v=LV6Juz0xcrY"
# μμ IDλ§ μ¨λ λ©λλ€
mcp-yt report LV6Juz0xcrYβ οΈ zsh μ¬μ©μ: URLμ
?κ° μμΌλ―λ‘ λ°λμ λ°μ΄νλ‘ κ°μΈμΈμ.
π 리ν¬νΈ μΆλ ₯ μμ
mcp-yt report "https://www.youtube.com/watch?v=LV6Juz0xcrY" μ€ν κ²°κ³Ό (extractive μμ½):
# πΉ Video Analysis Report: OpenClaw Use Cases that are Actually Helpful! (ClawdBot)
> Channel: Duncan Rogoff | AI Automation | Duration: 16:29 | Language: en_ytdlp
## 1. Summary
OpenClaw is the most powerful AI agent framework in the world right now and
it's about to replace your entire workflow. I spent over $200 in the last
48 hours stress testing the system so you don't have to. It defines who it
is, how it behaves, and crucial behavioral boundaries. If you think open
claw is cool, just check out this video up here of 63 insane use cases
that other people are doing.
## 2. Key Topics
| # | Topic | Keywords | Timespan |
|---|-------|----------|----------|
| 1 | framework, world, right | framework, world, right | 0:00~0:05 |
| 2 | like, really, there | like, really, there | 0:05~2:23 |
| 3 | like, max, using | like, max, using | 2:23~4:22 |
| 4 | going, like, something | going, like, something | 4:22~5:03 |
| 5 | like, agents, basically | like, agents, basically | 5:03~6:04 |
| ... | ... | ... | ... |
| 15 | think, open, claw | think, open, claw | 16:24~16:29 |
## 4. Keywords & Entities
- **Technology**: GitHub, LLM, GPT
- **Company**: Anthropic, Apple
## 5. Viewer Reactions
- Total comments: 20
- Sentiment: Positive 45% / Negative 0% / Neutral 55%
- Top opinions:
- **@geetee2583** (positive, π8): Great info. Just need your inset video out of the way...
- **@bdog4026** (positive, π3): This tool is wild! Definitely the most in depth explanation...
- **@magalyvilela4917** (neutral, π3): Came to this video wondering it gonna teach me how to set up...π CLI μ 체 λͺ λ Ήμ΄
π 리ν¬νΈ (ν΅μ¬ κΈ°λ₯)
β οΈ **리ν¬νΈμ μμ½ μΉμ μ LLM μ°λμ΄ νμμ λλ€. Ollama λΉ λ₯Έ μ€μ (무λ£, 3λΆμ΄λ©΄ λ):
# 1. Ollama μ€μΉ: https://ollama.ai # 2. λͺ¨λΈ λ€μ΄λ‘λ ollama pull qwen2.5:7b # 3. νκ²½λ³μ μ€μ export MYI_LLM_PROVIDER=ollama export MYI_OLLAMA_MODEL=qwen2.5:7b # μ격 μλ²λΌλ©΄ νΈμ€νΈλ μ§μ export MYI_OLLAMA_BASE_URL=http://your-server:11434
mcp-yt report "https://youtube.com/watch?v=VIDEO_ID"
mcp-yt report VIDEO_ID --provider ollama # LLM νλ‘λ°μ΄λ μ§μ
mcp-yt report VIDEO_ID --no-comments # λκΈ μ μΈ
mcp-yt report VIDEO_ID -o report.md # νμΌ μ μ₯π― μλ§ μΆμΆ + μμ½
mcp-yt transcript VIDEO_ID # μμ½ (~200β500 ν ν°)
mcp-yt transcript VIDEO_ID --mode full # μ 체 μλ§
mcp-yt transcript VIDEO_ID --mode chunks # μ²ν¬ λΆν
mcp-yt --json transcript VIDEO_ID # JSON μΆλ ₯κΈ°ν
mcp-yt video VIDEO_ID # λ©νλ°μ΄ν°
mcp-yt comments VIDEO_ID --max 20 # λκΈ (κ°μ± λΆμ ν¬ν¨)
mcp-yt entities VIDEO_ID # μν°ν° μΆμΆ
mcp-yt segments VIDEO_ID # ν ν½ μΈκ·Έλ©ν
μ΄μ
mcp-yt search "ν€μλ" --max 5 # YouTube κ²μ
mcp-yt monitor subscribe @μ±λνΈλ€ # μ±λ λͺ¨λν°λ§
mcp-yt playlist PLAYLIST_ID # νλ μ΄λ¦¬μ€νΈ
mcp-yt batch ID1 ID2 ID3 # λ°°μΉ μ²λ¦¬
mcp-yt search-transcripts "ν€μλ" # μ μ₯λ μλ§ κ²μπ‘ λͺ¨λ λͺ λ Ήμ΄μ
--jsonνλκ·Έλ₯Ό μΆκ°νλ©΄ JSON μΆλ ₯λ©λλ€.
π MCP μλ² μ°κ²°
MCP μλ²λ stdio νλ‘ν μ½λ‘ ν΅μ ν©λλ€.
Claude Desktop / Cursor / OpenCode
μ€μ νμΌμ μΆκ° (claude_desktop_config.json, .cursor/mcp.json, mcp.json):
{
"mcpServers": {
"youtube": {
"command": "uvx",
"args": ["mcp-youtube-intelligence"],
"env": {
"MYI_LLM_PROVIDER": "ollama",
"MYI_OLLAMA_MODEL": "qwen2.5:7b"
}
}
}
}π‘
uvxλuvν¨ν€μ§ λ§€λμ μ μ€ν λͺ λ Ήμ΄μ λλ€.pip install uvλ‘ μ€μΉνμΈμ.ν΄λΌμ°λ LLMμ μ°λ €λ©΄
envμ API ν€λ₯Ό μΆκ°νλ©΄ λ©λλ€:"OPENAI_API_KEY": "sk-..."
Claude Code
claude mcp add youtube -- uvx mcp-youtube-intelligenceMCP Tools (9κ°)
Tool | μ€λͺ | μμ ν ν° |
| λ©νλ°μ΄ν° + μμ½ | ~200β500 |
| μλ§ (summary/full/chunks) | ~200β500 |
| λκΈ + κ°μ± λΆμ | ~200β500 |
| RSS μ±λ λͺ¨λν°λ§ | ~100β300 |
| μ μ₯λ μλ§ κ²μ | ~100β400 |
| μν°ν° μΆμΆ | ~150β300 |
| ν ν½ λΆν | ~100β250 |
| YouTube κ²μ | ~200 |
| νλ μ΄λ¦¬μ€νΈ λΆμ | ~200β500 |
get_video
νλΌλ―Έν° | νμ | νμ | μ€λͺ |
| string | β | YouTube μμ ID |
get_transcript
νλΌλ―Έν° | νμ | νμ | κΈ°λ³Έκ° | μ€λͺ |
| string | β | β | YouTube μμ ID |
| string | β |
|
|
get_comments
νλΌλ―Έν° | νμ | νμ | κΈ°λ³Έκ° | μ€λͺ |
| string | β | β | YouTube μμ ID |
| int | β |
| λ°νν λκΈ μ |
| bool | β |
| μμ½ λ·° |
monitor_channel
νλΌλ―Έν° | νμ | νμ | κΈ°λ³Έκ° | μ€λͺ |
| string | β | β | μ±λ URL/@νΈλ€/ID |
| string | β |
|
|
search_transcripts
νλΌλ―Έν° | νμ | νμ | κΈ°λ³Έκ° | μ€λͺ |
| string | β | β | κ²μ ν€μλ |
| int | β |
| μ΅λ κ²°κ³Ό μ |
extract_entities / segment_topics
νλΌλ―Έν° | νμ | νμ | μ€λͺ |
| string | β | YouTube μμ ID |
search_youtube
νλΌλ―Έν° | νμ | νμ | κΈ°λ³Έκ° | μ€λͺ |
| string | β | β | κ²μ ν€μλ |
| int | β |
| μ΅λ κ²°κ³Ό μ |
| string | β |
|
|
get_playlist
νλΌλ―Έν° | νμ | νμ | κΈ°λ³Έκ° | μ€λͺ |
| string | β | β | νλ μ΄λ¦¬μ€νΈ ID |
| int | β |
| μ΅λ μμ μ |
βοΈ μ€μ
LLM νλ‘λ°μ΄λ μ€μ
LLM μμ΄λ κΈ°λ³Έ μμ½(ν΅μ¬ λ¬Έμ₯ μΆμΆ)μ λμν©λλ€. κ³ νμ§ μμ½μ μνλ©΄:
Ollama (μΆμ² β 무λ£, μ€νλΌμΈ)
# 1. Ollama μ€μΉ: https://ollama.ai
# 2. λͺ¨λΈ λ€μ΄λ‘λ
ollama pull qwen2.5:7b
# 3. νκ²½λ³μ μ€μ
export MYI_LLM_PROVIDER=ollama
export MYI_OLLAMA_MODEL=qwen2.5:7b
# 4. (μ ν) μ격 Ollama μλ² μ¬μ© μ
export MYI_OLLAMA_BASE_URL=http://your-server:11434ν΄λΌμ°λ LLM
# API ν€λ§ μ€μ νλ©΄ μλ κ°μ§ (MYI_LLM_PROVIDER=auto)
export OPENAI_API_KEY=sk-... # OpenAI
export ANTHROPIC_API_KEY=sk-ant-... # Anthropic
export GOOGLE_API_KEY=AIza... # Google
# νΉμ νλ‘λ°μ΄λ μ§μ
export MYI_LLM_PROVIDER=anthropicν΄λΌμ°λ LLM ν¨ν€μ§:
pip install "mcp-youtube-intelligence[llm]"(OpenAI) /[anthropic-llm]/[google-llm]/[all-llm]
μΆμ² Ollama λͺ¨λΈ
λͺ©μ | λͺ¨λΈ | ν¬κΈ° | νκ΅μ΄ | μμ΄ | νμ§ |
λ€κ΅μ΄ (μΆμ²) |
| 4.4GB | β | β | βββ |
μμ΄ μ€μ¬ |
| 4.7GB | β οΈ | β | βββ |
νκ΅μ΄ νΉν |
| 5.4GB | β | β | βββ |
κ²½λ |
| 1.9GB | β | β | ββ |
λ€κ΅μ΄ νΉν |
| 4.8GB | β | β | βββ |
β±οΈ μ€μΈ‘ λ²€μΉλ§ν¬
RTX 3070 8GB Β· Ollama Β· νκ΅μ΄ μλ§ ~2,900μ (5λΆ 19μ΄ μμ)
load_durationμ μΈ, μμ μμ± μκ° κΈ°μ€
λͺ¨λΈ | Prompt μ²λ¦¬ | μμ± μκ° | μλ | μΆλ ₯ | νμ§ |
Extractive | - | μ¦μ | - | 379μ | ββ |
qwen2.5:1.5b | 7.8s | 4.7s | 30.4 tok/s | 232μ | ββ |
qwen2.5:7b | 34.5s | 18.8s | 7.3 tok/s | 766μ | βββ |
aya-expanse:8b | 29.5s | 34.5s | 6.2 tok/s | 405μ | βββ |
β οΈ μ²« μ€ν μ λͺ¨λΈ λ‘λμ 15~60μ΄ μΆκ°.
keep_aliveλ‘ λ©λͺ¨λ¦¬ μ μ§νλ©΄ μ΄ν λ‘λ μμ.
νκ²½λ³μ | κΈ°λ³Έκ° | μ€λͺ |
|
| λ°μ΄ν° λλ ν 리 |
|
|
|
|
| SQLite κ²½λ‘ |
| β | PostgreSQL DSN |
|
| yt-dlp κ²½λ‘ |
|
| μ΅λ λκΈ μ |
|
|
|
| β | OpenAI ν€ |
|
| OpenAI λͺ¨λΈ |
| β | Anthropic ν€ |
|
| Anthropic λͺ¨λΈ |
| β | Google ν€ |
|
| Google λͺ¨λΈ |
|
| Ollama URL |
|
| Ollama λͺ¨λΈ |
|
| vLLM URL |
| β | vLLM λͺ¨λΈ |
|
| LM Studio URL |
| β | LM Studio λͺ¨λΈ |
π νΈλ¬λΈμν
λ¬Έμ | ν΄κ²° |
| URLμ λ°μ΄νλ‘ κ°μΈκΈ°: |
|
|
μλ§ μλ μμ |
|
SQLite database locked | μλ² μΈμ€ν΄μ€ νλλ§ μ€ν μ€μΈμ§ νμΈ |
LLM μμ½ μ€ν¨ | μλμΌλ‘ extractive ν΄λ°±λ¨. API ν€ νμΈ. |
π€ Contributing
git clone https://github.com/JangHyuckYun/mcp-youtube-intelligence.git
cd mcp-youtube-intelligence
pip install -e ".[dev]"
pytest tests/ -vπ λΌμ΄μ μ€
Apache 2.0 β LICENSE
π λ³κ²½ μ΄λ ₯
λ μ§ | λ²μ | μ£Όμ λ³κ²½ |
2025-02-18 | v0.1.0 | μ΄κΈ° λ¦΄λ¦¬μ€ β 9κ° MCP λꡬ, CLI, SQLite |
2025-02-18 | v0.1.1 | Multi-LLM (OpenAI/Anthropic/Google), Apache 2.0 |
2025-02-18 | v0.1.2 | Local LLM (Ollama/vLLM/LM Studio), yt-dlp μλ§ κ°μ , μμ΄ κΈ°λ³Έ μΆλ ₯ |
2025-02-18 | v0.1.3 | Local LLM (Ollama/vLLM/LM Studio), yt-dlp μλ§ κ°μ , μμ΄ κΈ°λ³Έ μΆλ ₯ |