Namu Watcher

Namu Watcher

Enables monitoring of Namu Wiki real-time search trends, including top keywords, explanations, historical data, and velocity detection.

Category
Visit Server

README

Namu Watch πŸ”

AI둜 λ‚˜λ¬΄μœ„ν‚€λ₯Ό 읽닀

Namu WatchλŠ” AI 챗봇이 μ‚¬μš©μžμ˜ μžμ—°μ–΄ μš”μ²­μ— 따라 λ‚˜λ¬΄μœ„ν‚€ λ¬Έμ„œλ₯Ό κ²€μƒ‰ν•˜κ³  읽을 수 있게 ν•΄μ£ΌλŠ” MCP μ„œλ²„μž…λ‹ˆλ‹€.

"λ‚˜λ¬΄μœ„ν‚€μ—μ„œ μ΄μˆœμ‹  μ•Œλ €μ€˜" β€” 이 ν•œλ§ˆλ””λ‘œ AIκ°€ λ‚˜λ¬΄μœ„ν‚€ λ¬Έμ„œλ₯Ό μ°Ύμ•„ μš”μ•½ν•΄μ€λ‹ˆλ‹€. μ‹€μ‹œκ°„ 검색어 νŠΈλ Œλ“œμ™€ 각 ν‚€μ›Œλ“œκ°€ μ™œ λœ¨λŠ”μ§€λ„ ν•¨κ»˜ 확인할 수 μžˆμŠ΅λ‹ˆλ‹€.


μ£Όμš” κΈ°λŠ₯

κΈ°λŠ₯ 도ꡬλͺ… μ„€λͺ…
πŸ” λ‚˜λ¬΄μœ„ν‚€ 검색 search λ‚˜λ¬΄μœ„ν‚€ λ¬Έμ„œ 검색 및 λ‚΄μš© 쑰회 (8000자 λ‹¨μœ„ 청크 λΆ„ν• , 멀티블둝 응닡). 핡심 κΈ°λŠ₯
πŸ”₯ μ‹€μ‹œκ°„ 검색어 trending λ‚˜λ¬΄μœ„ν‚€ 곡식 API 기반 μ‹€κ²€ TOP N 쑰회
❓ μ™œ λ–΄λŠ”μ§€ why νŠΉμ • ν‚€μ›Œλ“œκ°€ 싀검에 였λ₯Έ 이유 μ„€λͺ… (μ•„μΉ΄λΌμ΄λΈŒ β†’ λ‚˜λ¬΄μœ„ν‚€ fallback)
πŸ“… κ³Όκ±° 이λ ₯ history νŠΉμ • λ‚ μ§œμ˜ μ‹€κ²€ μˆœμœ„ λ˜λŠ” ν‚€μ›Œλ“œ μ‹œκ°„λ³„ λ“±μž₯ 기둝
πŸ“ˆ κΈ‰μƒμŠΉ 감지 velocity 졜근 Nμ‹œκ°„ λ™μ•ˆ 쑰회수 급증 ν‚€μ›Œλ“œ 탐지
πŸ”— μ—°κ΄€ ν‚€μ›Œλ“œ related νŠΉμ • ν‚€μ›Œλ“œμ™€ ν•¨κ»˜ 자주 λ“±μž₯ν•˜λŠ” μ—°κ΄€ ν‚€μ›Œλ“œ
πŸ‘« ν•¨κ»˜ νŠΈλ Œλ”© trending_together λ™μ‹œκ°„λŒ€ ν•¨κ»˜ λ“±μž₯ν•˜λŠ” ν‚€μ›Œλ“œ 쌍 뢄석
πŸ“Š 였늘의 리포트 trend_of_day 였늘의 μ‹€κ²€ μ’…ν•© 리포트

μ‚¬μš© μ˜ˆμ‹œ

μ‚¬μš©μžλŠ” μΉ΄μΉ΄μ˜€ν†‘ μ±„νŒ…μ—μ„œ μžμ—°μ–΄λ‘œ μ§ˆλ¬Έν•˜λ©΄ λ©λ‹ˆλ‹€. λͺ¨λ“  λͺ…λ Ήμ–΄λŠ” AIκ°€ μžλ™μœΌλ‘œ μΈμ‹ν•©λ‹ˆλ‹€.

πŸ‘€ "λ‚˜λ¬΄μœ„ν‚€μ—μ„œ μ΄μˆœμ‹ μ— λŒ€ν•΄ μ•Œλ €μ€˜"
β†’ AIκ°€ search("μ΄μˆœμ‹ ") 호좜 β†’ λ¬Έμ„œ 전체λ₯Ό 청크 λ‹¨μœ„λ‘œ μˆ˜μ‹ 
πŸ€– "μ΄μˆœμ‹ μ€ μ‘°μ„  μ€‘κΈ°μ˜ λ¬΄μ‹ μœΌλ‘œ..."

πŸ‘€ "ㄱㄱㅅ이 λˆ„κ΅¬μ•Ό?"
β†’ AIκ°€ search("γ„±γ„±γ……") 호좜 β†’ fallback chain: "γ„±γ„±γ……" β†’ "γ„±γ„±" β†’ μ μ ˆν•œ λ¬Έμ„œ 탐색
πŸ€– "κ³ κ΅¬λ§ˆμˆœμ΄λΌκ³ λ„ λΆˆλ¦¬λŠ”..."

πŸ‘€ "μ§€κΈˆ μ‹€κ²€ 뭐 뜨고 μžˆμ–΄?"
β†’ AIκ°€ trending() 호좜 β†’ λ‚˜λ¬΄μœ„ν‚€ 곡식 μ‹€κ²€ API
πŸ€– "πŸ”₯ μ‹€μ‹œκ°„ 검색어 TOP 10..."

πŸ‘€ "ν˜Έλ‚ λ‘ μ™œ 싀검에 λ–΄μ–΄?"
β†’ AIκ°€ why("ν˜Έλ‚ λ‘") 호좜 β†’ μ•„μΉ΄λΌμ΄λΈŒ κ²Œμ‹œκΈ€ 검색 β†’ λ‚˜λ¬΄μœ„ν‚€ fallback
πŸ€– "였늘 슀페인과의 16강전에 μ„ λ°œ μΆœμ „ν–ˆμœΌλ‚˜..."

데이터 μ†ŒμŠ€

기술 μŠ€νƒ

ν•­λͺ© 기술
μ–Έμ–΄ TypeScript (Node.js 20+)
λŸ°νƒ€μž„ Node.js 20+ (ESM, "type": "module")
MCP ν”„λ‘œν† μ½œ Streamable HTTP β€” POST /mcp (JSON-RPC 2.0)
HTTP μ„œλ²„ Node.js λ‚΄μž₯ http λͺ¨λ“ˆ
HTML νŒŒμ‹± cheerio
λ°μ΄ν„°λ² μ΄μŠ€ sql.js (SQLite β†’ WASM, λ„€μ΄ν‹°λΈŒ λΉŒλ“œ λΆˆν•„μš”)
μž…λ ₯ 검증 zod
배포 Docker (linux/amd64)

λΉ λ₯Έ μ‹œμž‘

사전 μš”κ΅¬μ‚¬ν•­

  • Node.js 20+
  • npm

μ„€μΉ˜ 및 μ‹€ν–‰

git clone https://github.com/mwl313/NamuWatcher.git
cd NamuWatcher

npm install
npm run build
node dist/index.js

μ„œλ²„κ°€ http://localhost:3000μ—μ„œ μ‹€ν–‰λ©λ‹ˆλ‹€.

Docker

docker build --platform linux/amd64 -t namu-watch .
docker run --platform linux/amd64 -p 3000:3000 -v namu-data:/app/data namu-watch

API μ—”λ“œν¬μΈνŠΈ

λ©”μ„œλ“œ 경둜 μ„€λͺ…
POST /mcp MCP Streamable HTTP (JSON-RPC 2.0)
GET /healthz ν—¬μŠ€μ²΄ν¬ (μƒνƒœ JSON λ°˜ν™˜)
OPTIONS * CORS preflight

MCP ν”„λ‘œν† μ½œ

ν΄λΌμ΄μ–ΈνŠΈλŠ” ν‘œμ€€ MCP JSON-RPC λ©”μ‹œμ§€λ₯Ό POST /mcp둜 μ „μ†‘ν•©λ‹ˆλ‹€.

μ΄ˆκΈ°ν™”:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {
    "protocolVersion": "2025-03-26",
    "capabilities": {},
    "clientInfo": { "name": "my-client", "version": "1.0.0" }
  }
}

도ꡬ 쑰회:

{ "jsonrpc": "2.0", "id": 2, "method": "tools/list" }

도ꡬ 호좜 (예: search):

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "search",
    "arguments": { "keyword": "μ΄μˆœμ‹ " }
  }
}

응닡 ν˜•μ‹ (search 도ꡬ)

search λ„κ΅¬λŠ” 멀티블둝 응닡을 λ°˜ν™˜ν•©λ‹ˆλ‹€.

{
  "jsonrpc": "2.0",
  "id": 3,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "{\"type\":\"search\",\"title\":\"μ΄μˆœμ‹ \",\"url\":\"...\",\"total_chunks\":5}"
      },
      {
        "type": "text",
        "text": "[1/5]\nμ΄μˆœμ‹ μ€ μ‘°μ„  μ€‘κΈ°μ˜ λ¬΄μ‹ μœΌλ‘œ..."
      },
      {
        "type": "text",
        "text": "[2/5]\n1592λ…„ μž„μ§„μ™œλž€μ΄ λ°œλ°œν•˜μž..."
      }
    ]
  }
}
  • 첫 번째 블둝: 메타정보 JSON (title, url, total_chunks)
  • 이후 블둝: [i/total] 라벨 + 8000자 λ‹¨μœ„ λ³Έλ¬Έ
  • AIλŠ” 메타정보λ₯Ό 읽고, ν•„μš”ν•œ 청크λ₯Ό μ„ νƒν•˜μ—¬ 닡변을 μƒμ„±ν•©λ‹ˆλ‹€.

ν™˜κ²½ λ³€μˆ˜

λ³€μˆ˜ κΈ°λ³Έκ°’ μ„€λͺ…
PORT 3000 HTTP μ„œλ²„ 포트
DB_PATH /app/data/namu_watch.db SQLite 파일 경둜
NODE_ENV production μ‹€ν–‰ λͺ¨λ“œ

ν”„λ‘œμ νŠΈ ꡬ쑰

namu-watch/
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ index.ts               # HTTP μ„œλ²„ + JSON-RPC ν•Έλ“€λŸ¬
β”‚   β”œβ”€β”€ types.ts               # 곡톡 νƒ€μž… μ •μ˜
β”‚   β”œβ”€β”€ utils.ts               # μœ ν‹Έλ¦¬ν‹° ν•¨μˆ˜ (fetch, delay, μΉ΄ν…Œκ³ λ¦¬ λΆ„λ₯˜)
β”‚   β”œβ”€β”€ tools/
β”‚   β”‚   β”œβ”€β”€ search.ts          # πŸ” λ‚˜λ¬΄μœ„ν‚€ λ¬Έμ„œ 검색 (청크 λΆ„ν•  + 멀티블둝 응닡)
β”‚   β”‚   β”œβ”€β”€ trending.ts        # πŸ”₯ λ‚˜λ¬΄μœ„ν‚€ 곡식 API μ‹€κ²€ TOP N
β”‚   β”‚   β”œβ”€β”€ why.ts             # ❓ μ‹€κ²€ 이유 μ„€λͺ… (μ•„μΉ΄λΌμ΄λΈŒ β†’ λ‚˜λ¬΄μœ„ν‚€ fallback)
β”‚   β”‚   β”œβ”€β”€ history.ts         # πŸ“… κ³Όκ±° μ‹€κ²€ 이λ ₯ 쑰회
β”‚   β”‚   β”œβ”€β”€ velocity.ts        # πŸ“ˆ κΈ‰μƒμŠΉ ν‚€μ›Œλ“œ 감지
β”‚   β”‚   β”œβ”€β”€ related.ts         # πŸ”— μ—°κ΄€ ν‚€μ›Œλ“œ
β”‚   β”‚   β”œβ”€β”€ trending-together.ts  # πŸ‘« ν•¨κ»˜ λœ¨λŠ” ν‚€μ›Œλ“œ
β”‚   β”‚   └── trend-of-day.ts    # πŸ“Š μ’…ν•© 리포트
β”‚   β”œβ”€β”€ scrapers/
β”‚   β”‚   β”œβ”€β”€ namuwiki.ts        # πŸ“– λ‚˜λ¬΄μœ„ν‚€ λ¬Έμ„œ νŒŒμ‹± (3단계 우회: 직행 β†’ μΏ ν‚€ β†’ Google Cache)
β”‚   β”‚   β”œβ”€β”€ ranking.ts         # πŸ“Š search.namu.wiki 곡식 μ‹€κ²€ API
β”‚   β”‚   └── arca.ts            # πŸ›οΈ μ•„μΉ΄λΌμ΄λΈŒ 싀검채널 μŠ€ν¬λž˜ν•‘ (vrow ꡬ쑰)
β”‚   └── db/
β”‚       β”œβ”€β”€ schema.ts          # SQLite μ΄ˆκΈ°ν™” (snapshots + articles)
β”‚       └── queries.ts         # DB CRUD ν•¨μˆ˜
β”œβ”€β”€ Dockerfile
β”œβ”€β”€ package.json
└── tsconfig.json

λΌμ΄μ„ μŠ€

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured