cb-strategy-mcp
可转债高级策略 MCP Server — 双低/三低/YTM/强赎/下修6大策略引擎,基于东方财富实时数据
Documentation
📊 可转债高级策略 MCP Server
> 6 大策略引擎,一键筛选全市场可转债
🚀 快速开始
pip install cb-strategy-mcp
# 以 MCP Server 方式运行
cb-strategy-mcp🧩 6 大策略工具
| 工具 | 说明 |
|---|---|
| `cb_market_overview` | 市场总览 — 均价、中位数、溢价率、价格区间分布 |
| `cb_dual_low` | 📉 双低策略 — 转股溢价率 + 价格双低排序,稳健首选 |
| `cb_triple_low` | 📊 三低策略 — 双低 + 小规模,游资最爱 |
| `cb_ytm_ranking` | 💰 到期收益率排名 — 寻找最靠近债底的标的 |
| `cb_redemption_monitor` | 🔥 强赎监控 — 谁快被强制赎回了 |
| `cb_revision_analysis` | 🔍 下修博弈分析 — 正股跌过头,公司可能下修 |
📈 数据来源
- 东方财富 (EastMoney) — 全市场 ~1000 只可转债实时数据
- 数据缓存 2 分钟,$0 成本
- 集思录数据源备用 (cookie 可选)
💡 策略说明
双低策略
双低值 = 转股溢价率 × 0.5 + (现价 / 100) × 50
筛选: 90-130元, 溢价率 ≤ 50%, 剔除退市债三低策略
三低值 = 双低 × 0.7 - 规模得分 × 3
额外: 发行规模 ≤ 10亿🔧 MCP 配置
在 `claude_desktop_config.json` 中添加:
{
"mcpServers": {
"cb-strategy-mcp": {
"command": "cb-strategy-mcp"
}
}
}📦 PyPI
pip install cb-strategy-mcp🏗️ 本地开发
git clone https://github.com/Lozzi1910/cb-strategy-mcp
cd cb-strategy-mcp
uv venv --python python3.11
source .venv/bin/activate
uv pip install -e .📄 许可证
MIT
🌟 项目路线图
- [x] 双低策略
- [x] 三低策略
- [x] YTM 排名
- [x] 强赎监控
- [x] 下修博弈分析
- [ ] 集思录 cookie 登录 → 获取纯债价值等精算数据
- [ ] 双低轮动回测
- [ ] 网格交易提醒
- [ ] 新债打新提醒
- [ ] 实时行情 WebSocket
Frequently asked questions
What is cb-strategy-mcp?
cb-strategy-mcp is 可转债高级策略 MCP Server — 双低/三低/YTM/强赎/下修6大策略引擎,基于东方财富实时数据
How do I install cb-strategy-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is cb-strategy-mcp open source?
Yes — it is hosted on GitHub at https://github.com/Lozzi1910/cb-strategy-mcp and has 3 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP