MCP Stocks Analyzer
Provides real-time stock data, news, company fundamentals, and technical indicators for AI assistants via the Model Context Protocol.
README
MCP Stocks Analyzer
A simple and efficient Model Context Protocol (MCP) server for financial analysis. This tool provides real-time stock data and news aggregation for AI assistants.
Features
- News: Fetch stock news from Google News.
- Prices: Get historical OHLCV data from Yahoo Finance.
- Company info: Read fundamentals and profile data.
- Technical indicators: Compute trend, momentum, volatility, and volume signals.
- MCP-ready: Designed to plug into AI assistants.
Installation
-
Clone the repository:
git clone https://github.com/vashishtavarma/mcp-stocks-analyzer.git cd mcp-stocks-analyzer -
Create and activate a virtual environment:
python -m venv venv # On Windows: venv\Scripts\activate # On macOS/Linux: source venv/bin/activate -
Install dependencies:
pip install -r requirements.txt
Usage
-
Start the MCP server:
python main.py -
Use the available tools from your MCP client:
get_news_from_google(ticker, region='IN', period='7d')get_stock_price(symbol, period, interval)get_company_info(symbol)get_technical_indicators(symbol, period='6mo', interval='1d')
Project Structure
main.py: MCP server entry point that registers tools.src/news.py: News fetching tool.src/price.py: Price history tool.src/company.py: Company info tool.src/indicators.py: Technical indicators tool.
Claude Desktop Setup
To integrate MCP Stocks Analyzer with Claude Desktop, follow these steps:
-
Locate the Configuration File:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- Windows:
-
Add the Server Configuration: Insert the following JSON snippet into the
mcpServersobject in the configuration file:{ "mcpServers": { "stock-analyzer": { "command": "<path>/mcp-stocks-analyzer/venv/bin/python", "args": [ "<path>/mcp-stocks-analyzer/main.py" ] } } }Note for Windows users: Adjust the python path to
...\\venv\\Scripts\\python.exeand use backslashes.Important: Replace
<path>with the absolute path to your project directory. -
Restart Claude Desktop: Restart the application to apply the changes. The MCP Stocks Analyzer tools will now be available in Claude Desktop.
License
This project is licensed under the MIT License. See the LICENSE file for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。