Unusual Whales MCP Server
Provides access to the Unusual Whales API for real-time financial data, options flow analysis, dark pool activity, and congressional trading tracking. It enables users to perform comprehensive market intelligence and stock analysis across 33 different tools.
README
Unusual Whales MCP Server
A Model Context Protocol (MCP) server that provides access to the Unusual Whales API for financial data, options flow analysis, and market intelligence.
Features
- 🚀 Fast and lightweight - Direct API access without heavy dependencies
- 📊 Comprehensive data - 33 tools covering 12 financial data categories
- 🔄 Real-time insights - Options flow alerts, market sentiment, and live data
- 🏛️ Congressional tracking - Monitor politician trading activity
- 🌊 Dark pool analysis - Track institutional block trades
- 📈 Market intelligence - ETF flows, earnings data, and volatility metrics
Requirements
- Node.js 18+
- Valid Unusual Whales API key
- Compatible with Claude Desktop, VS Code, and other MCP clients
Installation
The server is available as an npm package and can be installed in multiple ways:
Quick Start
npx unusualwhales-mcp
Global Installation
npm install -g unusualwhales-mcp
Local Installation
npm install unusualwhales-mcp
Configuration
Environment Setup
- Obtain an API key from Unusual Whales
- Set the environment variable:
export UNUSUAL_WHALES_API_KEY=your_api_key_here
Or create a .env file:
UNUSUAL_WHALES_API_KEY=your_api_key_here
MCP Client Configuration
Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"unusualwhales": {
"command": "npx",
"args": ["unusualwhales-mcp"],
"env": {
"UNUSUAL_WHALES_API_KEY": "your_api_key_here"
}
}
}
}
VS Code (via MCP extension)
{
"mcpServers": {
"unusualwhales": {
"command": "npx",
"args": ["unusualwhales-mcp"]
}
}
}
Other MCP Clients
The server works with any MCP-compatible client. Use the command:
npx unusualwhales-mcp
Available Tools
📊 Stock Analysis
get_stock_info- Get comprehensive stock informationget_stock_flow_alerts- Get options flow alerts for a tickerget_stock_flow_recent- Get recent options flowsget_stock_option_chains- Get option chains dataget_stock_greek_exposure- Get Greeks exposure analysisget_stock_max_pain- Get max pain calculationsget_stock_iv_rank- Get IV rank percentilesget_stock_volatility_stats- Get volatility statistics
🌊 Market Data
get_market_tide- Get overall market sentiment indicatorget_market_economic_calendar- Get economic events calendarget_market_fda_calendar- Get FDA calendar eventsget_market_spike- Get SPIKE volatility indicatorget_market_total_options_volume- Get market-wide options volume
🏛️ Congressional & Insider Trading
get_congress_trader- Get congress member trading dataget_congress_late_reports- Get late filing reportsget_congress_recent_trades- Get recent congressional trades
🌑 Dark Pool Analysis
get_darkpool_recent- Get recent dark pool printsget_darkpool_ticker- Get dark pool data for specific ticker
📈 ETF Analysis
get_etf_exposure- Get ETF sector/geographic exposureget_etf_holdings- Get ETF holdings breakdownget_etf_in_outflow- Get ETF flow dataget_etf_info- Get ETF informationget_etf_weights- Get ETF sector weights
📅 Earnings & Events
get_earnings_afterhours- Get after-hours earningsget_earnings_premarket- Get pre-market earningsget_earnings_ticker- Get historical earnings for ticker
🔔 Alerts & Screening
get_alerts- Get triggered user alertsget_alerts_configuration- Get alert configurationsget_option_trades_flow_alerts- Get options flow alertsget_screener_analysts- Get analyst ratings screenerget_screener_option_contracts- Get hottest chains screenerget_screener_stocks- Get stock screener results
📰 News
get_news_headlines- Get financial news headlines
Usage Examples
Basic Stock Analysis
// Get recent options flows for AAPL
const flows = await server.callTool("get_stock_flow_recent", {
ticker: "AAPL"
});
// Get comprehensive stock info
const info = await server.callTool("get_stock_info", {
ticker: "TSLA"
});
Market Sentiment
// Get overall market sentiment
const tide = await server.callTool("get_market_tide", {});
// Get volatility spike indicator
const spike = await server.callTool("get_market_spike", {});
Congressional Trading
// Get recent congressional trades for NVDA
const congressTrades = await server.callTool("get_congress_recent_trades", {
ticker: "NVDA"
});
// Get trades by specific congress member
const memberTrades = await server.callTool("get_congress_trader", {
name: "Nancy Pelosi"
});
Dark Pool Activity
// Get recent dark pool activity
const darkPool = await server.callTool("get_darkpool_recent", {
limit: 50
});
// Get dark pool data for specific ticker
const tickerDarkPool = await server.callTool("get_darkpool_ticker", {
ticker: "SPY"
});
Using as a Package in Node.js Projects
This package can be imported and used directly in your Node.js applications, including web frameworks like Hono, Express, or Fastify.
Installation as Dependency
npm install unusualwhales-mcp
Basic Usage
import { UnusualWhalesMcp } from 'unusualwhales-mcp';
// Create MCP server instance
const mcpServer = new UnusualWhalesMcp();
// Get the server instance for integration
const server = mcpServer.getServer();
// Start with different transport types
await mcpServer.start('stdio'); // For MCP clients
await mcpServer.start('sse', { endpoint: '/sse', response: res }); // For HTTP SSE
await mcpServer.start('streamableHttp'); // For HTTP streaming
Integration with Hono Web Framework
import { Hono } from 'hono';
import { cors } from 'hono/cors';
import { UnusualWhalesMcp } from 'unusualwhales-mcp';
const app = new Hono();
const mcpServer = new UnusualWhalesMcp();
// Enable CORS for MCP endpoints
app.use('/mcp/*', cors({
origin: '*',
allowHeaders: ['Content-Type'],
allowMethods: ['GET', 'POST', 'OPTIONS'],
}));
// SSE endpoint for MCP over HTTP
app.get('/mcp/sse', async (c) => {
const response = c.env?.response || c.res;
// Start MCP server with SSE transport
await mcpServer.start('sse', {
endpoint: '/mcp/sse',
response: response
});
return c.json({ status: 'SSE endpoint ready' });
});
// Streamable HTTP endpoint
app.post('/mcp/message', async (c) => {
try {
// Create streamable HTTP transport
const transport = mcpServer.createStreamableHTTPTransport({
sessionIdGenerator: () => crypto.randomUUID()
});
// Handle MCP message
const body = await c.req.json();
return c.json({
status: 'message processed',
sessionId: transport.sessionId
});
} catch (error) {
console.error('MCP endpoint error:', error);
return c.json({ error: 'Internal server error' }, 500);
}
});
// Direct API endpoints (bypassing MCP)
app.get('/api/stock/:ticker', async (c) => {
try {
const ticker = c.req.param('ticker');
const server = mcpServer.getServer();
// Call tool directly
const result = await server.callTool('get_stock_info', { ticker });
return c.json(result);
} catch (error) {
return c.json({ error: error.message }, 500);
}
});
export default {
port: 3000,
fetch: app.fetch,
};
Environment Configuration
# Set your Unusual Whales API key
export UNUSUAL_WHALES_API_KEY=your_api_key_here
# Optional: Configure server settings
export MCP_SERVER_NAME=unusualwhales-mcp
export MCP_SERVER_VERSION=0.1.3
Advanced Usage with Custom Transport
import { UnusualWhalesMcp } from 'unusualwhales-mcp';
import { SSEServerTransport } from '@modelcontextprotocol/sdk/server/sse.js';
const mcpServer = new UnusualWhalesMcp();
// Create custom SSE transport
const customTransport = new SSEServerTransport('/custom-endpoint', response);
// Connect server with custom transport
await mcpServer.getServer().connect(customTransport);
// Or use the helper methods
const sseTransport = mcpServer.createSSETransport('/my-endpoint', response);
const httpTransport = mcpServer.createStreamableHTTPTransport({
sessionIdGenerator: () => `session-${Date.now()}`
});
TypeScript Support
The package includes full TypeScript definitions:
import { UnusualWhalesMcp } from 'unusualwhales-mcp';
import type { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
const mcpServer: UnusualWhalesMcp = new UnusualWhalesMcp();
const server: McpServer = mcpServer.getServer();
// Full type safety for all API calls
const stockInfo = await server.callTool('get_stock_info', {
ticker: 'AAPL'
});
API Coverage
The server provides access to 81 API endpoints across 12 categories:
| Category | Endpoints | Description |
|---|---|---|
| Alerts | 2 | Custom alerts and configurations |
| Congress | 3 | Congressional trading data |
| Darkpool | 2 | Dark pool trading analysis |
| Earnings | 3 | Earnings calendars and data |
| ETFs | 5 | ETF analysis and holdings |
| Group Flow | 2 | Grouped options flow data |
| Insider | 4 | Insider trading information |
| Institutions | 6 | Institutional holdings and activity |
| Market | 9 | Market-wide data and indicators |
| Net Flow | 1 | Net options flow by expiry |
| News | 1 | Financial news headlines |
| Option Contract | 4 | Individual contract analysis |
| Option Trades | 2 | Options flow and alerts |
| Screeners | 3 | Stock and options screening tools |
| Seasonality | 4 | Seasonal market patterns |
| Shorts | 5 | Short interest and volume data |
| Stock | 27 | Comprehensive stock analysis |
Development
Local Development
# Clone the repository
git clone https://github.com/your-username/unusualwhales-mcp.git
cd unusualwhales-mcp
# Install dependencies
npm install
# Set up environment
cp .env.example .env
# Edit .env with your API key
# Build the project
npm run build
# Run the server
npm start
Available Scripts
npm run build- Compile TypeScript and make executablenpm run watch- Watch for changes and recompilenpm run inspector- Launch MCP inspector for debuggingnpm run prepare- Prepare package for publishing
Project Structure
unusualwhales-mcp/
├── src/
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript output
├── package.json # Project configuration
├── tsconfig.json # TypeScript configuration
template
└── README.md # This file
Rate Limits
Please be aware of Unusual Whales API rate limits. The server includes:
- 30-second timeout for requests
- Proper error handling for rate limit responses
- Retry logic for transient failures
License
This project is licensed under the MIT License - see the LICENSE file for details.
Disclaimer
⚠️ Important: This software is for educational and research purposes only. Always verify data independently before making trading decisions. The authors are not responsible for any financial losses incurred from using this software.
Support
- Issues: GitHub Issues
- API Documentation: Unusual Whales API Docs
Related Projects
- Model Context Protocol - Official MCP implementation
- Claude Desktop - AI assistant with MCP support
- Unusual Whales - Financial data platform
Made with ❤️ for unusualwhales
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。