quantdb-mcp

quantdb-mcp

Read-only SQL MCP server for quantitative finance data (DuckDB) with stock quotes, financials, and historical K-lines, enabling cross-database JOIN queries.

Category
Visit Server

README

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）。

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。

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured