quantdb-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@quantdb-mcp What are the latest stock prices and company names?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
quantdb-mcp
量化金融数据库 + 只读 SQL MCP 服务。
数据源:easy-tdx(通达信 TCP 行情)+ pywestockdata(腾讯/东财基本面 HTTP)
存储:DuckDB 双文件 ——
quantdb_ods.duckdb(ODS 原始层)/quantdb.duckdb(DWD 层,清洗后)接口:FastMCP streamable-http 只读
query(sql)工具(可跨库 JOIN)
分层架构
层 | 库文件 | 表 |
ODS | quantdb_ods.duckdb | stock_basic / daily_kline / realtime_quote / finance_income / finance_balance / finance_cashflow |
DWD | quantdb.duckdb | dim_stock(去重标准化)/ fact_daily(列名统一) |
APP | - | 后续因子层(可复用 factor-pipeline 表达式引擎) |
ODS 可整体重灌,DWD 由 sync_dwd 全量重建(幂等)。
Related MCP server: ashare-mcp
安装
cd projects/quantdb-mcp
uv sync # 或 pip install -e .依赖:duckdb、fastmcp、pywestockdata、easy-tdx、click。
CLI
quantdb init # 建库建表(双文件)
quantdb full-load # 全量同步:代码表 → 日K → 财务 → DWD 重建
quantdb full-load --codes 50 --kline-count 120 # 限前 50 只、每只 120 根K线(试跑用)
quantdb update --once # 增量同步 + 一次实时快照
quantdb update # 盘中 30s 快照循环(Ctrl+C 退出)
quantdb summary # 各表行数与最新日期数据目录通过环境变量 QUANTDB_DATA_DIR 指定(默认 ./data)。
MCP 接入
启动服务(streamable-http):
uv run python -m quantdb.server.mcp # 等价 pip 安装后的 quantdb-mcp注册到 MCP 客户端(如 nanobot / Claude Desktop):
{
"mcpServers": {
"quantdb": {
"command": "quantdb-mcp",
"type": "stdio"
}
}
}查询示例(query 工具,只读):
SELECT * FROM dim_stock WHERE market = 'sh' LIMIT 5
SELECT d.code, s.name, d.close FROM fact_daily d JOIN ods.stock_basic s ON d.code = s.code
WHERE d.date = (SELECT max(date) FROM fact_daily)安全限制
仅允许单条
SELECT/WITH;写语句、多语句被拒绝表白名单:仅业务表(ODS 用
ods.前缀),内部表不可见最多返回 10_000 行;查询超时 30s;DuckDB 以只读模式打开
测试
uv run pytest # 97 tests,100% 覆盖率(mock 数据源,不依赖网络)
uv run ruff check src tests # 0 error详见 design.md 与 task_list.md。
Available Tools
1 toolqueryA
对量化数据库执行只读 SQL 查询。
支持表:dim_stock、fact_daily、finance_income/balance/cashflow、 realtime_quote、stock_basic、daily_kline(ODS 表用 ods. 前缀)。 仅允许单条 SELECT/WITH;写语句与多语句会被拒绝;最多返回 10000 行。
Inputs: sql (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only a single tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as executing read-only SQL queries against a specified set of tables, so agents can directly know what it does.
The sole tool is named 'query', which is a simple, predictable, and consistent name. Since there is only one tool, there are no mixed conventions or inconsistent patterns to confuse an agent.
A single tool might seem thin, but it serves a comprehensive purpose as a generic SQL query interface covering many tables. While additional metadata tools could be useful, the count is slightly under but acceptable for a focused read-only database server.
The tool provides complete read-only access to all listed tables, supporting SELECT/WITH queries with a row limit. A minor gap is the lack of schema/metadata exploration tools, but the description partially fills this by listing the available tables, making it workable for most use cases.
Related MCP Connectors
China A-share market data over MCP: 22 tools for quotes, K-line, financials, money flow, top-trader boards, sectors, macro, convertible bonds and factor screening. Five tools need no API key, so you can connect and try it immediately.
The stock market, in SQL — scan, replay, or subscribe across ~12k US tickers and top 100 cryptos.
China A-share market data for research, backtesting and AI agents via MCP.
Historical tick, order book and settlement data for Polymarket and Predict.fun crypto up/down markets, plus smart-money lists and backtest quotes, over a read-only MCP server.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenance基于Model Context Protocol (MCP) 的A股实时行情查询服务器,支持查询A股实时价格、历史K线数据、财务信息及市场概况。8MIT
- AlicenseAqualityBmaintenanceA-share market data MCP server via baostock. Full-stack coverage: K-line, financials, DCF/DDM/PEG valuation, 11 technical indicators with proper split-day volume handling (OBV/MFI on raw bars), CN-style KDJ (J=3K-2D), risk metrics (Beta/Sharpe/MaxDD with stock-suspension-aware aligned returns), and PBoC macro data.2511MIT
- AlicenseAqualityCmaintenanceRead-only MCP server for large-scale cross-sectional quant analysis of US stock market data (1.49 billion rows) using ClickHouse.7MIT
- AlicenseBqualityBmaintenanceMCP server that syncs and queries comprehensive stock data (quotes, financials, dividends, analyst forecasts, options, news) from Yahoo Finance and Investing.com into an external MySQL database.27148 npmMIT