aigroup-finnhub-mcp
A Node.js MCP server that wraps the Finnhub API to provide stock market data, technical analysis, news sentiment, and cryptocurrency market information.
README
aigroup-finnhub-mcp
Node.js MCP server for Finnhub financial market data.
Overview
aigroup-finnhub-mcp provides a practical MCP wrapper around the Finnhub API for:
- stock quotes and candles
- company profiles and fundamentals
- technical indicators and trading signals
- news, sentiment, and insider sentiment
- crypto market data
Highlights
- 15 MCP tools grouped by market data, technical analysis, fundamentals, news, and crypto
- TypeScript + Zod validation for safer input handling
- Built-in rate limiting with retry logic
- Structured error handling for more reliable downstream use
- Designed for MCP clients such as Claude Desktop and similar tools
Quick Start
Requirements
- Node.js >= 18
- npm
- A valid Finnhub API key
Install and build
git clone https://github.com/jackdark425/aigroup-finnhub-mcp.git
cd aigroup-finnhub-mcp
npm install
npm run build
Configure API key
FINNHUB_API_KEY=your_api_key_here npm start
You can get an API key from Finnhub Dashboard.
Configuration
If you use a local .env file:
cp .env.example .env
Then set:
FINNHUB_API_KEY=your_api_key_here
MCP Client Configuration
Using npx
{
"mcpServers": {
"aigroup-finnhub": {
"command": "npx",
"args": ["-y", "aigroup-finnhub-mcp"],
"env": {
"FINNHUB_API_KEY": "your_finnhub_api_key_here"
}
}
}
}
Using local build output
{
"mcpServers": {
"aigroup-finnhub": {
"command": "node",
"args": ["/path/to/aigroup-finnhub-mcp/dist/index.js"],
"env": {
"FINNHUB_API_KEY": "your_finnhub_api_key_here"
}
}
}
}
Tool Groups
| Tool | Operations | Description |
|---|---|---|
finnhub_stock_market_data |
7 | Quotes, candles, profiles, financials |
finnhub_technical_analysis |
4 | Indicators, patterns, signals |
finnhub_news_sentiment |
4 | News and sentiment workflows |
finnhub_stock_fundamentals |
5 | Financial metrics, dividends, splits |
finnhub_crypto_data |
4 | Crypto exchanges, symbols, prices |
API Reference
finnhub_stock_market_data
get_quoteget_candlesget_company_profilesymbol_lookupget_basic_financialsget_financials_as_reportedget_earnings_surprises
finnhub_technical_analysis
get_indicatorget_aggregate_signalsget_pattern_recognitionget_support_resistance
finnhub_news_sentiment
get_company_newsget_market_newsget_news_sentimentget_insider_sentiment
Development
npm run typecheck
npm run lint
npm run test
Acknowledgments
Reference Project
- cfdude/mcp-finnhub
- Repository: https://github.com/cfdude/mcp-finnhub
- Reference scope: overall project direction, MCP server structure, and interface organization
Thanks to cfdude for the prior open-source work that helped inform this implementation.
License & Usage
This project is released under the MIT License.
You may use, copy, modify, merge, publish, distribute, sublicense, and sell copies of this software, including for commercial use, as long as the original copyright notice and license text are preserved.
Please note:
- the software is provided "AS IS", without warranty of any kind
- you must retain the license and copyright notice in copies or substantial portions of the software
- usage of the Finnhub API remains subject to Finnhub's own terms of service, rate limits, and data licensing restrictions
See the full text in LICENSE.
Support
- Issues: https://github.com/jackdark425/aigroup-finnhub-mcp/issues
- Repository: https://github.com/jackdark425/aigroup-finnhub-mcp
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。