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., "@Stock MCP Server What's the current price of Tencent (hk00700) and Tesla (usTSLA)?"
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.
腾讯股票数据 MCP 服务器，为 AI 助手提供股票数据查询和持仓管理功能。
A股实时行情（上海、深圳）
港股实时行情
美股实时行情
支持批量查询
添加、更新、删除持仓
查询持仓列表和详情
添加、更新、删除关注股票
查询观察列表
Related MCP server: xueqiu-mcp
代码 | 市场 |
sh | 上海A股 |
sz | 深圳A股 |
hk | 港股 |
us | 美股 |
市场 | 每手股数 |
A股普通 | 100股 |
A股科创板(688开头) | 200股 |
港股 | 取数据第61位 |
美股 | 1股 |
npm installnpm run build在 Claude Code 或其他 MCP 客户端的配置文件中添加：
{
"mcpServers": {
"stock": {
"command": "node",
"args": ["/path/to/stock-mcp/dist/index.js"]
}
}
}// 查询股票行情
stock_get({ symbol: "sh000001" })
// 批量查询
stock_get_batch({ symbols: ["sh000001", "sz000001"] })
// 添加持仓
position_add({ symbol: "sz000001", shares: 100, cost: 10.5 })
// 添加观察
watch_add({ symbol: "hk00700", note: "腾讯控股" })工具 | 描述 |
| 获取单只股票实时行情 |
| 批量获取多只股票行情 |
| 添加持仓 |
| 更新持仓 |
| 删除持仓 |
| 获取所有持仓 |
| 获取单个持仓 |
| 添加观察股票 |
| 更新观察股票 |
| 删除观察股票 |
| 获取所有观察 |
| 获取单个观察 |
TypeScript
Node.js
@modelcontextprotocol/sdk
股票数据来自 腾讯财经 API
MIT
添加持仓记录
Inputs: code (required), name (required), quantity (required), costPrice (required), +2 more.
获取单个持仓记录
Inputs: code (required), market (required).
获取所有持仓记录
Inputs: no named parameters.
删除持仓记录
Inputs: code (required), market (required).
更新持仓记录（数量或成本价）
Inputs: code (required), market (required), quantity, costPrice.
获取单只股票实时行情数据
Inputs: code (required), market (required).
批量获取多只股票实时行情数据
Inputs: stocks (required).
添加观察股票
Inputs: code (required), name (required), reason (required), market (required).
获取单个观察股票
Inputs: code (required), market (required).
获取所有观察股票
Inputs: no named parameters.
删除观察股票
Inputs: code (required), market (required).
更新观察股票（名称或观察理由）
Inputs: code (required), market (required), name, reason.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 12 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools are organized into three logical groups (position, stock, watch) with specific CRUD operations for each, making it easy for an agent to select the correct tool for any task.
The tool names follow a perfectly consistent verb_noun pattern throughout, using snake_case uniformly. Each group maintains the same naming convention (e.g., position_add, stock_get, watch_list), making the set highly predictable and readable.
With 12 tools, this server is well-scoped for stock management. Each tool earns its place by covering essential operations for positions, stock data, and watchlists, without being overly sparse or bloated for the domain.
The tool surface provides complete CRUD/lifecycle coverage for the stock management domain. It includes all necessary operations for positions, real-time stock data, and watchlists, with no obvious gaps that would cause agent failures.
Access real-time and historical market data for China A-shares and Hong Kong stocks, along with ne…
Provide access to Chinese stock market data including historical prices, real-time data, news, and…
China A-share data for AI agents: 57 read-only tools plus 6 tools for your own watchlist.
Real-time quotes, fuzzy search and K-line history across 13 global stock markets.
