Local Stock Analyst MCP

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.

Category
访问服务器

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:

  • stdio mode for local Claude Desktop integration (default)
  • HTTP mode for cloud hosting (for example, Render)

Tools

  • get_stock_price
  • get_quote
  • get_company_profile
  • get_candles
  • get_stock_news
  • get_rsi
  • get_macd
  • get_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

Setup

  1. Install dependencies:
npm install
  1. Create env file from template:
copy .env.example .env
  1. 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.

  1. Push this project to GitHub.
  2. In Render, create a new Web Service from your repo.
  3. Configure:
    • Build Command: npm install && npm run build
    • Start Command: npm start
  4. Add environment variables:
    • MCP_TRANSPORT=http
    • FINNHUB_API_KEY=... (optional but recommended)
    • ALPHAVANTAGE_API_KEY=... (optional fallback)
    • PORT is auto-provided by Render.
  5. Deploy.

After deploy, verify:

  • https://<your-service>.onrender.com/healthz returns {"status":"ok"}
  • MCP server endpoint is https://<your-service>.onrender.com/mcp

Quick Test Prompts in Claude

  • "Call get_stock_price for MSFT."
  • "Call get_candles for MSFT, interval D, from 1704067200, to 1735689600, limit 5."
  • "Call get_rsi for MSFT, interval D, from 1704067200, to 1735689600."

Troubleshooting

  • No tools visible in Claude
    • Check JSON validity of claude_desktop_config.json.
    • Confirm build/index.js exists (npm run build).
    • Fully restart Claude Desktop.
  • Auth errors
    • Verify API keys in config env or local .env.
  • 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

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选