Builds a local financial database based on tushare. An AI-native multi-Agent financial analysis system that supports skill-based Agent extensions and adaptively generates HTTP interfaces and MCP calls. Supports skills with local database access and connects general-purpose agents such as deepseek-harness/openclaw and IM channels including WeChat, QQ, and Feishu for market monitoring.
This repository also configures its own agents. See what stock_datasource tells them →
Skill Claude CodeCodex
This skill should be used when the user needs to set up, manage, or troubleshoot MCP API Key authentication and tool usage tracking for this stock data service. Use it when configuring external MCP clients (Claude Code, Cursor) to connect to the data service.
Skill Claude CodeCodex needs its repo
A stock-data assistant that combines historical market-data queries, live price updates, and access through WeChat. It covers Chinese and Hong Kong stocks, ETFs, indexes, and related data.
Skill Claude CodeCodex
Query historical stock market data (A-shares, HK stocks, ETFs, indices) via MCP. Use when the user wants daily K-line, financial statements, market indicators, screening, or other batch data. DeepSeek Harness clients should call stocklisttools then stockcalltool. Remote HTTP MCP on port 8001 still requires…
Skill Claude CodeCodex
Subscribe to real-time stock market data via WebSocket long connection from receiver nodes (A-shares, HK stocks, ETFs). Use this skill when the user wants to monitor live stock prices, set up real-time alerts, or stream minute-level K-line data. The skill provides a WebSocket server that connects to receiver nodes and…
Skill Claude CodeCodex
This skill should be used when the user provides a Tushare API document URL and asks to generate a full plugin in this codebase, including extractor, schema, config, query service, and agent/MCP/http usage with testable curl examples.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: