FinanceNews
A Model Context Protocol (MCP) server that provides financial news search capabilities. This server enables AI assistants to fetch and analyze financial news from various sources based on user queries.
claude mcp add --transport stdio guangxiangdebizi-financenews-mcp node build/index.js \ --env PORT="3000" \ --env NODE_ENV="development" \ --env LOG_LEVEL="info" \ --env NEWS_API_KEY="your_news_api_key (optional; for alternative sources if configured)" \ --env FINNHUB_API_KEY="your_finnhub_api_key (optional; recommended for production if using Finnhub directly)" \ --env CACHE_TTL_SECONDS="300" \ --env RATE_LIMIT_WINDOW_MS="900000" \ --env ALPHA_VANTAGE_API_KEY="your_alpha_vantage_key (optional)" \ --env RATE_LIMIT_MAX_REQUESTS="100"
How to use
FinanceNews MCP is a server that provides real-time financial news search capabilities to AI assistants through the MCP protocol. It exposes a single tool named get_financial_news, which accepts a query string and returns relevant financial news articles sourced from Finnhub (with actual API data when keys are configured) and related metadata. To use it, run the server, then configure your MCP client to point to the server's MCP endpoint (typically /mcp) with a suitable timeout. The client can invoke get_financial_news by sending an MCP-compatible request containing the tool name and arguments, for example a query like 'Tesla stock earnings'. You can also configure HTTP headers to pass API keys or tenant information if needed. The integration examples show Claude Desktop and other MCP clients capable of streaming HTTP MCP endpoints with optional headers for authentication.
How to install
Prerequisites:
- Node.js 18.0.0 or higher
- npm or yarn
Install from npm (recommended for quick start):
-
Install globally (optional): npm install -g financenews-mcp
-
Start from npm (from source after building): git clone https://github.com/guangxiangdebizi/FinanceNews-MCP.git cd FinanceNews-MCP npm install npm run build npm run start:http
Install from source (full build):
-
Clone the repository git clone https://github.com/guangxiangdebizi/FinanceNews-MCP.git cd FinanceNews-MCP
-
Install dependencies npm install
-
Build the project npm run build
-
Run the server (development or production)
- Development: npm run dev
- Production: npm run start:http
Note: The MCP server exposes the endpoint at http://localhost:3000/mcp by default. Adjust the PORT via environment variables if needed.
Additional notes
Tips and common considerations:
- Ensure you have a valid Finnhub API key if you plan to fetch real-time news data. Configure FINNHUB_API_KEY in the environment or pass it via request headers as described in the README.
- Environment variables control port, rate limiting, caching, and log level. Typical defaults are PORT=3000, RATE_LIMIT_WINDOW_MS=900000, RATE_LIMIT_MAX_REQUESTS=100, CACHE_TTL_SECONDS=300, LOG_LEVEL=info.
- If you interrupt the server, use npm run start:http again or npm run dev for development hot-reload.
- When deploying with Docker or PM2, ensure the build artifacts (build/index.js) are present or compiled in the deployment image.
- The server uses a real data source (Finnhub) when API keys are configured; without keys it will clearly indicate missing API configuration and guide on setup.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
FinanceMCP
这是一个金融领域相关的mcp,本项目通过集成 Tushare API 和 Binance API 为语言模型(如Claude)提供全面的实时金融数据访问能力,支持股票、基金、债券、宏观经济指标、稳定币、虚拟货币等多维度金融数据分析。其中也包含了金融数据查询、财经新闻查询、国家统计局数据查询等
mcp-trader
A Model Context Protocol (MCP) server for stock traders
TradingAgents mode
TradingAgents-MCPmode 是一个创新的多智能体交易分析系统,集成了 Model Context Protocol (MCP) 工具,实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作,提供全面的市场分析、投资建议和风险管理。
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!