基于雪球数据源的 MCP 服务器，提供 A 股行情查询、K 线数据和技术指标计算
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"xueqiu-stock-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 雪球 A 股 MCP 服务器 基于雪球(Xueqiu)数据源的 MCP 服务器，提供 A 股实时行情、K 线技术指标、盘口、财务数据查询。 ## 安装 ```bash pip3 install xueqiu-stock-mcp xueqiu-stock --setup ``` **第一步**（~10 秒）：安装 MCP 服务器本体，体积小，无重依赖。 **第二步**（~2 分钟）：`--setup` 自动安装 Playwright + Chromium 浏览器（约 150MB）。这是雪球 API 的必需依赖（用于绕过阿里云 WAF）。 > 如果 `xueqiu-stock` 命令找不到，用 `python3 -m xueqiu_stock --setup` ## MCP 配置 ```json { "mcpServers": { "xueqiu-stock": { "command": "xueqiu-stock" } } } ``` 配置文件位置： - **Claude Desktop**: `~/.claude/claude_desktop_config.json` - **Cursor**: 项目根目录 `/.cursor/mcp.json` - **VS Code**: 项目根目录 `/.vscode/mcp.json` - **QwenPaw**: `~/.qwenpaw/config.json` → `mcp.clients` ## 提供的工具 | 工具 | 功能 | |------|------| | `get_stock_quote` | 实时行情（价格、涨跌幅、PE/PB、市值等） | | `get_kline_data` | K 线数据 + 技术指标（MA/MACD/RSI/BOLL/KDJ） | | `get_minute_data` | 分时走势（逐分钟价格和成交量） | | `get_pankou_data` | 五档盘口（买卖五档价格和数量） | | `get_financial` | 财务报表（利润表/资产负债表/现金流量表） | ## 命令 ```bash xueqiu-stock # 启动 MCP 服务器 xueqiu-stock --setup # 安装依赖（Playwright + Chromium） xueqiu-stock --check # 检查依赖是否就绪 ``` ## 故障排除 **`pip3` 也没有？** ```bash python3 -m pip install xueqiu-stock-mcp ``` **启动报错"缺少 playwright"？** ```bash xueqiu-stock --setup ``` **`--setup` 很慢？** Chromium 下载约 150MB，首次需要下载。如网络慢可手动下载：https://playwright.dev/python/docs/intro#installing-browsers ## PyPI https://pypi.org/project/xueqiu-stock-mcp/
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.