MCP News Collector

MCP News Collector

A Model Context Protocol server that collects and analyzes Korean stock market news in real-time, providing investment insights through AI-based analysis of sentiment, market impact, and rumor detection.

Category
Visit Server

README

πŸ“° MCP News Collector

ν•œκ΅­ μ£Όμ‹μ‹œμž₯ λ‰΄μŠ€ μ‹€μ‹œκ°„ μˆ˜μ§‘ 및 뢄석을 μœ„ν•œ MCP μ„œλ²„

Python FastAPI License Tests

🎯 ν”„λ‘œμ νŠΈ κ°œμš”

MCP News CollectorλŠ” ν•œκ΅­ μ£Όμ‹μ‹œμž₯ κ΄€λ ¨ λ‰΄μŠ€λ₯Ό μ‹€μ‹œκ°„μœΌλ‘œ μˆ˜μ§‘, λΆ„μ„ν•˜μ—¬ 투자 μΈμ‚¬μ΄νŠΈλ₯Ό μ œκ³΅ν•˜λŠ” MCP(Model Context Protocol) μ„œλ²„μž…λ‹ˆλ‹€.

✨ μ£Όμš” κΈ°λŠ₯

  • πŸ”„ μ‹€μ‹œκ°„ λ‰΄μŠ€ μˆ˜μ§‘: 넀이버, λ‹€μŒ, RSS ν”Όλ“œ λ“± λ‹€μ–‘ν•œ μ†ŒμŠ€
  • 🧠 AI 기반 뢄석: 감정 뢄석, μ‹œμž₯ 영ν–₯도 예츑, 루머 탐지
  • πŸ“Š μ‹€μ‹œκ°„ λͺ¨λ‹ˆν„°λ§: WebSocket 기반 μ‹€μ‹œκ°„ 데이터 슀트리밍
  • 🌐 REST API: FastAPI 기반 RESTful μ—”λ“œν¬μΈνŠΈ
  • πŸ”§ MCP 톡합: Claude λ“± AI μ–΄μ‹œμŠ€ν„΄νŠΈμ™€ μ›ν™œν•œ 연동

πŸ—οΈ μ•„ν‚€ν…μ²˜

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚   Data Sources  β”‚    β”‚   MCP Server    β”‚    β”‚   AI Assistant  β”‚
β”‚                 β”‚    β”‚                 β”‚    β”‚                 β”‚
β”‚ β€’ 넀이버 λ‰΄μŠ€   │────▢│ β€’ μˆ˜μ§‘ μ—”μ§„     │◀───│ β€’ Claude        β”‚
β”‚ β€’ λ‹€μŒ λ‰΄μŠ€     β”‚    β”‚ β€’ 뢄석 μ—”μ§„     β”‚    β”‚ β€’ ChatGPT       β”‚
β”‚ β€’ RSS ν”Όλ“œ      β”‚    β”‚ β€’ REST API      β”‚    β”‚ β€’ 기타          β”‚
β”‚ β€’ λΉ…μΉ΄μΈμ¦ˆ      β”‚    β”‚ β€’ WebSocket     β”‚    β”‚                 β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸš€ λΉ λ₯Έ μ‹œμž‘

사전 μš”κ΅¬μ‚¬ν•­

  • Python 3.11+
  • PostgreSQL 13+
  • Redis 6+

μ„€μΉ˜

# 1. μ €μž₯μ†Œ 클둠
git clone https://github.com/YOUR_USERNAME/mcp-news-collector.git
cd mcp-news-collector

# 2. κ°€μƒν™˜κ²½ 생성 및 ν™œμ„±ν™”
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# 3. μ˜μ‘΄μ„± μ„€μΉ˜
pip install -e .

# 4. ν™˜κ²½λ³€μˆ˜ μ„€μ •
cp .env.example .env
# .env νŒŒμΌμ„ νŽΈμ§‘ν•˜μ—¬ λ°μ΄ν„°λ² μ΄μŠ€ 및 API μ„€μ •

# 5. λ°μ΄ν„°λ² μ΄μŠ€ λ§ˆμ΄κ·Έλ ˆμ΄μ…˜
alembic upgrade head

# 6. μ„œλ²„ μ‹€ν–‰
python -m src.server.main

MCP ν΄λΌμ΄μ–ΈνŠΈ μ—°κ²°

from mcp import Client

# MCP μ„œλ²„ μ—°κ²°
client = Client("stdio", ["python", "-m", "src.server.main"])

# λ‰΄μŠ€ μˆ˜μ§‘
result = await client.call_tool("get_recent_news", {
    "keyword": "μ‚Όμ„±μ „μž",
    "limit": 10
})

πŸ“– API λ¬Έμ„œ

MCP Tools

Tool μ„€λͺ… νŒŒλΌλ―Έν„°
get_recent_news 졜근 λ‰΄μŠ€ 쑰회 keyword, source, limit, hours
analyze_news_sentiment λ‰΄μŠ€ 감정 뢄석 news_id, text, detail_level
analyze_news_impact μ‹œμž₯ 영ν–₯도 뢄석 news_id, company, timeframe
detect_market_rumors 루머 탐지 news_id, threshold
monitor_news_stream μ‹€μ‹œκ°„ λ‰΄μŠ€ λͺ¨λ‹ˆν„°λ§ topics, filters

REST API

API λ¬Έμ„œλŠ” μ„œλ²„ μ‹€ν–‰ ν›„ λ‹€μŒ URLμ—μ„œ 확인할 수 μžˆμŠ΅λ‹ˆλ‹€:

  • Swagger UI: http://localhost:8000/api/docs
  • ReDoc: http://localhost:8000/api/redoc

μ£Όμš” μ—”λ“œν¬μΈνŠΈ

# λ‰΄μŠ€ 쑰회
GET /api/v1/news?query=μ‚Όμ„±μ „μž&limit=10

# 감정 뢄석
POST /api/v1/analysis/sentiment
{
  "news_ids": ["news_1", "news_2"],
  "options": {"include_confidence": true}
}

# μ‹€μ‹œκ°„ λͺ¨λ‹ˆν„°λ§ μƒνƒœ
GET /api/v1/monitoring/status

πŸ§ͺ ν…ŒμŠ€νŠΈ

# 전체 ν…ŒμŠ€νŠΈ μ‹€ν–‰
pytest

# νŠΉμ • λͺ¨λ“ˆ ν…ŒμŠ€νŠΈ
pytest tests/unit/test_sentiment_analyzer.py

# 컀버리지 확인
pytest --cov=src --cov-report=html

ν…ŒμŠ€νŠΈ ν˜„ν™©

  • 전체 ν…ŒμŠ€νŠΈ: 169개 톡과
  • 컀버리지:
    • 감정 뢄석기: 92%
    • μ‹œμž₯ 영ν–₯ 뢄석기: 85%
    • μ‹€μ‹œκ°„ λͺ¨λ‹ˆν„°λ§: 76%
    • 루머 탐지: 89%
    • λ‰΄μŠ€ μš”μ•½: 90%

πŸ“Š 개발 ν˜„ν™©

Phase 별 μ§„ν–‰ 상황

  • βœ… Phase 1: 기초 인프라 ꡬ좕 (μ™„λ£Œ)
  • βœ… Phase 2: 핡심 μˆ˜μ§‘ μ‹œμŠ€ν…œ (μ™„λ£Œ)
  • βœ… Phase 3: 뢄석 μ—”μ§„ κ΅¬ν˜„ (μ™„λ£Œ)
  • πŸ”„ Phase 4: API 및 톡합 μ‹œμŠ€ν…œ (75% μ™„λ£Œ)
  • ⏳ Phase 5: μ΅œμ ν™” 및 배포 (μ˜ˆμ •)

μžμ„Έν•œ 개발 κ³„νšμ€ detailed-development-plan.mdλ₯Ό μ°Έμ‘°ν•˜μ„Έμš”.

πŸ—οΈ ν”„λ‘œμ νŠΈ ꡬ쑰

mcp-news-collector/
β”œβ”€β”€ src/                    # 메인 μ†ŒμŠ€ μ½”λ“œ
β”‚   β”œβ”€β”€ analysis/          # 뢄석 μ—”μ§„ (감정, 영ν–₯도, 루머 탐지 λ“±)
β”‚   β”œβ”€β”€ collectors/        # λ‰΄μŠ€ μˆ˜μ§‘κΈ° (넀이버, λ‹€μŒ, RSS)
β”‚   β”œβ”€β”€ monitoring/        # μ‹€μ‹œκ°„ λͺ¨λ‹ˆν„°λ§ μ‹œμŠ€ν…œ
β”‚   β”œβ”€β”€ server/            # MCP μ„œλ²„ 및 REST API
β”‚   └── utils/             # 곡톡 μœ ν‹Έλ¦¬ν‹°
β”œβ”€β”€ tests/                 # ν…ŒμŠ€νŠΈ μ½”λ“œ
β”‚   β”œβ”€β”€ unit/              # λ‹¨μœ„ ν…ŒμŠ€νŠΈ
β”‚   └── integration/       # 톡합 ν…ŒμŠ€νŠΈ
β”œβ”€β”€ docs/                  # λ¬Έμ„œ
β”œβ”€β”€ configs/               # μ„€μ • 파일
└── scripts/               # μœ ν‹Έλ¦¬ν‹° 슀크립트

πŸ”§ 개발 도ꡬ

μ½”λ“œ ν’ˆμ§ˆ

# μ½”λ“œ ν¬λ§·νŒ…
black src/ tests/

# νƒ€μž… 체킹
mypy src/

# λ¦°νŒ…
pylint src/

# λ³΄μ•ˆ μŠ€μΊ”
bandit -r src/

TDD 개발 ν”„λ‘œμ„ΈμŠ€

이 ν”„λ‘œμ νŠΈλŠ” μ—„κ²©ν•œ TDD(Test-Driven Development) 방법둠을 λ”°λ¦…λ‹ˆλ‹€:

  1. Red: μ‹€νŒ¨ν•˜λŠ” ν…ŒμŠ€νŠΈ μž‘μ„±
  2. Green: ν…ŒμŠ€νŠΈλ₯Ό ν†΅κ³Όμ‹œν‚€λŠ” μ΅œμ†Œν•œμ˜ μ½”λ“œ μž‘μ„±
  3. Refactor: μ½”λ“œ κ°œμ„  및 μ΅œμ ν™”

🀝 κΈ°μ—¬ν•˜κΈ°

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

개발 κ°€μ΄λ“œλΌμΈ

  • λͺ¨λ“  μƒˆλ‘œμš΄ κΈ°λŠ₯은 ν…ŒμŠ€νŠΈμ™€ ν•¨κ»˜ 개발
  • μ½”λ“œ 컀버리지 80% 이상 μœ μ§€
  • νƒ€μž… 힌트 μ‚¬μš© ν•„μˆ˜
  • λ¬Έμ„œν™” μ² μ €νžˆ

πŸ“„ λΌμ΄μ„ μŠ€

이 ν”„λ‘œμ νŠΈλŠ” MIT λΌμ΄μ„ μŠ€ ν•˜μ— λ°°ν¬λ©λ‹ˆλ‹€. μžμ„Έν•œ λ‚΄μš©μ€ LICENSE νŒŒμΌμ„ μ°Έμ‘°ν•˜μ„Έμš”.

πŸ“ž 문의

πŸ™ κ°μ‚¬μ˜ 말


⭐ 이 ν”„λ‘œμ νŠΈκ°€ 도움이 λ˜μ…¨λ‹€λ©΄ Starλ₯Ό λˆŒλŸ¬μ£Όμ„Έμš”!

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
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
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
VeyraX MCP

VeyraX MCP

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

Official
Featured
Local
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
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
Qdrant Server

Qdrant Server

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

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
E2B

E2B

Using MCP to run code via e2b.

Official
Featured