Local Stock Analyst MCP
Provides a suite of stock analysis tools for Claude, enabling real-time price tracking, financial data retrieval, and technical indicator calculations like RSI and MACD. It leverages Finnhub and Alpha Vantage APIs to deliver comprehensive market insights through the Model Context Protocol.
README
Local Stock Analyst MCP (stdio)
Local TypeScript MCP server for Claude Desktop that exposes stock-analysis tools using:
- Finnhub as the primary provider
- Alpha Vantage as fallback
- local indicator calculation fallback for RSI and MACD
The server supports:
stdiomode for local Claude Desktop integration (default)HTTPmode for cloud hosting (for example, Render)
Tools
get_stock_priceget_quoteget_company_profileget_candlesget_stock_newsget_rsiget_macdget_key_financials
Each tool validates input with zod, formats output consistently, and includes an informational disclaimer.
Requirements
- Node.js 20.x (recommended for Render stability)
- npm
- API key for at least one provider:
- Finnhub:
FINNHUB_API_KEY - Alpha Vantage:
ALPHAVANTAGE_API_KEY
- Finnhub:
Setup
- Install dependencies:
npm install
- Create env file from template:
copy .env.example .env
- Add your API keys to
.env.
Build and Run
Build:
npm run build
Start locally (stdio MCP mode):
npm start
Start in HTTP mode (Render-style):
set MCP_TRANSPORT=http
set PORT=3000
npm start
HTTP endpoints:
- MCP endpoint:
/mcp - health check:
/healthz
Claude Desktop (Windows) Configuration
Open your Claude Desktop config file:
%APPDATA%\Claude\claude_desktop_config.json
Add/update:
{
"mcpServers": {
"local-stock-analyst": {
"command": "node",
"args": ["D:/mcpserverdemo/mcplocalstock/build/index.js"],
"env": {
"FINNHUB_API_KEY": "YOUR_FINNHUB_KEY",
"ALPHAVANTAGE_API_KEY": "YOUR_ALPHA_VANTAGE_KEY"
}
}
}
}
Notes:
- Use absolute paths in
args. - Forward slashes are safe on Windows JSON paths.
- Restart Claude Desktop after saving config.
Deploy on Render
Use a Web Service deployment.
- Push this project to GitHub.
- In Render, create a new Web Service from your repo.
- Configure:
- Build Command:
npm install && npm run build - Start Command:
npm start
- Build Command:
- Add environment variables:
MCP_TRANSPORT=httpFINNHUB_API_KEY=...(optional but recommended)ALPHAVANTAGE_API_KEY=...(optional fallback)PORTis auto-provided by Render.
- Deploy.
After deploy, verify:
https://<your-service>.onrender.com/healthzreturns{"status":"ok"}- MCP server endpoint is
https://<your-service>.onrender.com/mcp
Quick Test Prompts in Claude
- "Call
get_stock_priceforMSFT." - "Call
get_candlesforMSFT, intervalD, from1704067200, to1735689600, limit5." - "Call
get_rsiforMSFT, intervalD, from1704067200, to1735689600."
Troubleshooting
- No tools visible in Claude
- Check JSON validity of
claude_desktop_config.json. - Confirm
build/index.jsexists (npm run build). - Fully restart Claude Desktop.
- Check JSON validity of
- Auth errors
- Verify API keys in config
envor local.env.
- Verify API keys in config
- Rate-limit errors
- Retry later, reduce call frequency, or use higher-tier keys.
- The server automatically attempts Alpha Vantage fallback after Finnhub failures.
Logs
- Claude Desktop logs are usually in
%APPDATA%\Claude\logs. - Server startup/errors are written to stderr by the MCP process.
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。