mh-fin-mcp
Enables China A-share quantitative market data retrieval, including market overview, industry rotation, sector hotspots, limit-up analysis, and risk alerts.
README
mh-fin-mcp
<!-- mcp-name: io.github.clk1st/mh-fin-mcp -->
MCP Server for China A-Share quantitative market data, powered by MetricHub Quant.
Features
- Market Overview: Major indices, limit-up/down stats, breadth, northbound flow, sentiment
- Industry Rotation: Shenwan industry ranking with up/down ratio and limit-up counts
- Sector Hotspots: Concept sector analysis with leading stocks
- Stock Data: Full daily data for 5000+ A-shares (OHLCV, PE, PB, market cap, money flow)
- Stock Search: Search by name or code
- Limit-Up Analysis: 13-factor quantitative scoring for limit-up stocks
- Factor IC: Factor effectiveness history
- Risk Alerts: Shareholder reduction, performance warnings
Quick Start
1. Get API Key
Register at quant.metrichub.app, then go to API Key management to create a key.
2. Choose your integration method
Option A: Remote Server (Recommended, zero install)
No installation needed. Just add the URL to your config:
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"mh-fin": {
"url": "https://api.quant.metrichub.app/mcp/sse",
"headers": {
"X-API-Key": "mhfk_your_key_here"
}
}
}
}
Claude Code (.claude/settings.json):
{
"mcpServers": {
"mh-fin": {
"url": "https://api.quant.metrichub.app/mcp/sse",
"headers": {
"X-API-Key": "mhfk_your_key_here"
}
}
}
}
Option B: Local Install (via PyPI)
pip install mh-fin-mcp
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"mh-fin": {
"command": "uvx",
"args": ["mh-fin-mcp"],
"env": {
"MH_FIN_API_KEY": "mhfk_your_key_here"
}
}
}
}
Claude Code (.claude/settings.json):
{
"mcpServers": {
"mh-fin": {
"command": "uvx",
"args": ["mh-fin-mcp"],
"env": {
"MH_FIN_API_KEY": "mhfk_your_key_here"
}
}
}
}
3. Restart Claude to activate
Available Tools
| Tool | Description |
|---|---|
get_trade_dates |
List available trade dates |
get_market_overview |
Market overview: indices, breadth, sentiment, northbound flow |
get_industry_ranking |
Industry rotation ranking (Shenwan industries) |
get_sector_hotspots |
Concept sector hotspots with leading stocks |
get_stock_list |
Paginated stock data for 5000+ A-shares |
search_stock |
Search stocks by name or code |
get_limitup_analysis |
Limit-up analysis with 13 quantitative factors |
get_factor_ic |
Factor IC effectiveness history |
get_risk_alerts |
Risk alerts (shareholder reduction, etc.) |
Data
- Covers all 5000+ A-shares
- Updated daily after 17:30 CST (Mon-Fri)
- 13 quantitative factors for limit-up scoring
- Data only, no investment advice
License
MIT
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。