MCP News Collector
Powers the RESTful API endpoints for accessing news data and analysis functionality
Supports project installation and contribution workflow through Git repository management
Provides issue tracking, documentation hosting, and collaboration features for the project
Stores collected news data and analysis results in a PostgreSQL database
Enables comprehensive testing of news collection and analysis functionality
Serves as the foundation programming language for the MCP server implementation
Provides caching and real-time data streaming capabilities for news monitoring
Collects news data from RSS feed sources for Korean stock market information
Generates status badges for the project documentation
Provides interactive API documentation through Swagger UI
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
π° MCP News Collector
νκ΅ μ£Όμμμ₯ λ΄μ€ μ€μκ° μμ§ λ° λΆμμ μν MCP μλ²
π― νλ‘μ νΈ κ°μ
MCP News Collectorλ νκ΅ μ£Όμμμ₯ κ΄λ ¨ λ΄μ€λ₯Ό μ€μκ°μΌλ‘ μμ§, λΆμνμ¬ ν¬μ μΈμ¬μ΄νΈλ₯Ό μ 곡νλ MCP(Model Context Protocol) μλ²μ λλ€.
β¨ μ£Όμ κΈ°λ₯
π μ€μκ° λ΄μ€ μμ§: λ€μ΄λ², λ€μ, RSS νΌλ λ± λ€μν μμ€
π§ AI κΈ°λ° λΆμ: κ°μ λΆμ, μμ₯ μν₯λ μμΈ‘, 루머 νμ§
π μ€μκ° λͺ¨λν°λ§: WebSocket κΈ°λ° μ€μκ° λ°μ΄ν° μ€νΈλ¦¬λ°
π REST API: FastAPI κΈ°λ° RESTful μλν¬μΈνΈ
π§ MCP ν΅ν©: Claude λ± AI μ΄μμ€ν΄νΈμ μνν μ°λ
ποΈ μν€ν μ²
βββββββββββββββββββ βββββββββββββββββββ βββββββββββββββββββ
β Data Sources β β MCP Server β β AI Assistant β
β β β β β β
β β’ λ€μ΄λ² λ΄μ€ ββββββΆβ β’ μμ§ μμ§ ββββββ β’ Claude β
β β’ λ€μ λ΄μ€ β β β’ λΆμ μμ§ β β β’ ChatGPT β
β β’ RSS νΌλ β β β’ REST API β β β’ κΈ°ν β
β β’ λΉ
μΉ΄μΈμ¦ β β β’ WebSocket β β β
βββββββββββββββββββ βββββββββββββββββββ βββββββββββββββββββRelated MCP server: MCP Stock Details Server
π λΉ λ₯Έ μμ
μ¬μ μꡬμ¬ν
Python 3.11+
PostgreSQL 13+
Redis 6+
μ€μΉ
# 1. μ μ₯μ ν΄λ‘
git clone https://github.com/YOUR_USERNAME/mcp-news-collector.git
cd mcp-news-collector
# 2. κ°μνκ²½ μμ± λ° νμ±ν
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# 3. μμ‘΄μ± μ€μΉ
pip install -e .
# 4. νκ²½λ³μ μ€μ
cp .env.example .env
# .env νμΌμ νΈμ§νμ¬ λ°μ΄ν°λ² μ΄μ€ λ° API μ€μ
# 5. λ°μ΄ν°λ² μ΄μ€ λ§μ΄κ·Έλ μ΄μ
alembic upgrade head
# 6. μλ² μ€ν
python -m src.server.mainMCP ν΄λΌμ΄μΈνΈ μ°κ²°
from mcp import Client
# MCP μλ² μ°κ²°
client = Client("stdio", ["python", "-m", "src.server.main"])
# λ΄μ€ μμ§
result = await client.call_tool("get_recent_news", {
"keyword": "μΌμ±μ μ",
"limit": 10
})π API λ¬Έμ
MCP Tools
Tool | μ€λͺ | νλΌλ―Έν° |
| μ΅κ·Ό λ΄μ€ μ‘°ν | keyword, source, limit, hours |
| λ΄μ€ κ°μ λΆμ | news_id, text, detail_level |
| μμ₯ μν₯λ λΆμ | news_id, company, timeframe |
| 루머 νμ§ | news_id, threshold |
| μ€μκ° λ΄μ€ λͺ¨λν°λ§ | topics, filters |
REST API
API λ¬Έμλ μλ² μ€ν ν λ€μ URLμμ νμΈν μ μμ΅λλ€:
Swagger UI:
http://localhost:8000/api/docsReDoc:
http://localhost:8000/api/redoc
μ£Όμ μλν¬μΈνΈ
# λ΄μ€ μ‘°ν
GET /api/v1/news?query=μΌμ±μ μ&limit=10
# κ°μ λΆμ
POST /api/v1/analysis/sentiment
{
"news_ids": ["news_1", "news_2"],
"options": {"include_confidence": true}
}
# μ€μκ° λͺ¨λν°λ§ μν
GET /api/v1/monitoring/statusπ§ͺ ν μ€νΈ
# μ 체 ν
μ€νΈ μ€ν
pytest
# νΉμ λͺ¨λ ν
μ€νΈ
pytest tests/unit/test_sentiment_analyzer.py
# 컀λ²λ¦¬μ§ νμΈ
pytest --cov=src --cov-report=htmlν μ€νΈ νν©
μ 체 ν μ€νΈ: 169κ° ν΅κ³Ό
컀λ²λ¦¬μ§:
κ°μ λΆμκΈ°: 92%
μμ₯ μν₯ λΆμκΈ°: 85%
μ€μκ° λͺ¨λν°λ§: 76%
루머 νμ§: 89%
λ΄μ€ μμ½: 90%
π κ°λ° νν©
Phase λ³ μ§ν μν©
β Phase 1: κΈ°μ΄ μΈνλΌ κ΅¬μΆ (μλ£)
β Phase 2: ν΅μ¬ μμ§ μμ€ν (μλ£)
β Phase 3: λΆμ μμ§ κ΅¬ν (μλ£)
π Phase 4: API λ° ν΅ν© μμ€ν (75% μλ£)
β³ Phase 5: μ΅μ ν λ° λ°°ν¬ (μμ )
μμΈν κ°λ° κ³νμ detailed-development-plan.mdλ₯Ό μ°Έμ‘°νμΈμ.
ποΈ νλ‘μ νΈ κ΅¬μ‘°
mcp-news-collector/
βββ src/ # λ©μΈ μμ€ μ½λ
β βββ analysis/ # λΆμ μμ§ (κ°μ , μν₯λ, 루머 νμ§ λ±)
β βββ collectors/ # λ΄μ€ μμ§κΈ° (λ€μ΄λ², λ€μ, RSS)
β βββ monitoring/ # μ€μκ° λͺ¨λν°λ§ μμ€ν
β βββ server/ # MCP μλ² λ° REST API
β βββ utils/ # κ³΅ν΅ μ νΈλ¦¬ν°
βββ tests/ # ν
μ€νΈ μ½λ
β βββ unit/ # λ¨μ ν
μ€νΈ
β βββ integration/ # ν΅ν© ν
μ€νΈ
βββ docs/ # λ¬Έμ
βββ configs/ # μ€μ νμΌ
βββ scripts/ # μ νΈλ¦¬ν° μ€ν¬λ¦½νΈπ§ κ°λ° λꡬ
μ½λ νμ§
# μ½λ ν¬λ§·ν
black src/ tests/
# νμ
체νΉ
mypy src/
# λ¦°ν
pylint src/
# 보μ μ€μΊ
bandit -r src/TDD κ°λ° νλ‘μΈμ€
μ΄ νλ‘μ νΈλ μ격ν TDD(Test-Driven Development) λ°©λ²λ‘ μ λ°λ¦ λλ€:
Red: μ€ν¨νλ ν μ€νΈ μμ±
Green: ν μ€νΈλ₯Ό ν΅κ³Όμν€λ μ΅μνμ μ½λ μμ±
Refactor: μ½λ κ°μ λ° μ΅μ ν
π€ κΈ°μ¬νκΈ°
Fork the repository
Create your feature branch (
git checkout -b feature/amazing-feature)Commit your changes (
git commit -m 'Add some amazing feature')Push to the branch (
git push origin feature/amazing-feature)Open a Pull Request
κ°λ° κ°μ΄λλΌμΈ
λͺ¨λ μλ‘μ΄ κΈ°λ₯μ ν μ€νΈμ ν¨κ» κ°λ°
μ½λ 컀λ²λ¦¬μ§ 80% μ΄μ μ μ§
νμ ννΈ μ¬μ© νμ
λ¬Έμν μ² μ ν
π λΌμ΄μ μ€
μ΄ νλ‘μ νΈλ MIT λΌμ΄μ μ€ νμ λ°°ν¬λ©λλ€. μμΈν λ΄μ©μ LICENSE νμΌμ μ°Έμ‘°νμΈμ.
π λ¬Έμ
κ°λ°μ: Your Name
μ΄μ νΈλ컀: GitHub Issues
νλ‘μ νΈ μν€: GitHub Wiki
π κ°μ¬μ λ§
MCP (Model Context Protocol) - Anthropic
FastAPI - SebastiΓ‘n Ramirez
KoBERT - SKT Brain
β μ΄ νλ‘μ νΈκ° λμμ΄ λμ ¨λ€λ©΄ Starλ₯Ό λλ¬μ£ΌμΈμ!
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Korean (DART/KIND) and US SEC filings with AI summaries, direction labels and market reaction.
Production MCP server for US equity and options intelligence: real-time IV radar, Monte Carlo simulation, options pressure, strategy backtesting, AI prediction, pre-trade risk analysis, and automated stock research reports.
China A-share & equity research MCP server (εε£°ζη ) for market quotes, filings, financials, fund flows, concepts & sentiment.
Real-time news with bias scoring, live market data, and AI-powered options pricing
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server that provides AI assistants access to stock market data including financial statements, stock prices, and market news through a Model Context Protocol interface.112,329MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server providing comprehensive Korean stock market analysis, including financial data, valuation metrics, ESG information, and investment insights.MIT
- FlicenseAqualityDmaintenanceMCP server that provides Korean stock market data including indices, top gainers, stock quotes, news, fundamentals, and buy recommendations. Enables LLMs to access real-time and historical Korean stock information.6-
- FlicenseNot gradedqualityCmaintenanceA remote Model Context Protocol (MCP) server for real-time cryptocurrency and stock market analysis. Provides AI-powered market intelligence tools with 9 theory-based analysis engines, multi-chain DEX discovery, and enterprise features.-