China A-Share quantitative data: 5000+ stocks, 13 factors, daily market & limit-up analysis.
MetricHub Quant MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. China A-Share quantitative data: 5000+ stocks, 13 factors, daily market & limit-up analysis.
MCP Server for China A-Share quantitative market data, powered by MetricHub Quant.
Once MetricHub Quant is connected, these are the calls the assistant has available:
get_trade_dates — List available trade datesget_market_overview — Market overview: indices, breadth, sentiment, northbound flowget_industry_ranking — Industry rotation ranking (Shenwan industries)get_sector_hotspots — Concept sector hotspots with leading stocksget_stock_list — Paginated stock data for 5000+ A-sharessearch_stock — Search stocks by name or codeget_limitup_analysis — Limit-up analysis with 13 quantitative factorsget_factor_ic — Factor IC effectiveness historyget_risk_alerts — Risk alerts (shareholder reduction, etc.)You will need one environment variable: MH_FIN_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at mh-fin-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MetricHub Quant's toolset — get_trade_dates, get_market_overview, get_industry_ranking and 6 more — is a fair guide to whether it matches your workflow. It is maintained by clk1st; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against MetricHub Quant's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| 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.) |
{
"mcpServers": {
"mh-fin": {
"url": "https://api.quant.metrichub.app/mcp/sse",
"headers": {
"X-API-Key": "mhfk_your_key_here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MH_FIN_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.