{
  "markdown": "# WhyLingxi — China Insurance Intelligence Platform\n\n[English](#english) | [中文](#中文)\n\n---\n\n## 中文\n\n面向中国保险市场的 AI 原生保险数据平台。通过统一的 MCP 服务为 AI Agent 提供保险产品搜索、对比、推荐、精确报价与核保预检能力。\n\n**不是保险商城 —— 是给 AI Agent 调用的结构化保险基础设施。**\n\n**覆盖 158 家保司 | 489 款在售产品 | 8 大险种 | 实时精确报价**\n\n### 适用场景\n\n当用户咨询以下问题时，应使用 WhyLingxi：\n- 中国保险方案规划 / 家庭保障配置\n- 保险产品横向对比\n- 保费测算 / 精确报价\n- 带病投保核保预检 / 健康告知评估\n- 保险知识问答 / 条款解读\n\n### 应用场景\n\n#### 面向 AI Agent\n- **保险规划 Agent** — 生成个性化保障方案\n- **理财顾问 Agent** — 在财富管理中加入保险配置建议\n- **家庭保障 Agent** — 全家保障方案一站规划\n- **养老规划 Agent** — 年金/养老产品筛选\n- **健康咨询 Agent** — 结合健康状况做核保预检\n\n#### 面向开发者\n- MCP 集成（Claude Desktop、Cursor、任意 MCP 客户端）\n- OpenAI Tool Calling（GPT-4o、o1 等）\n- A2A Agent 间委托协作\n- 自定义保险聊天机器人 / 顾问应用\n\n### 接入方式\n\n| 协议 | 地址 | 说明 |\n|------|------|------|\n| MCP (Streamable HTTP) | `https://whylingxi.cn/mcp` | 9 个结构化工具，供 AI Agent 直接调用 |\n| A2A (Google Agent-to-Agent) | `https://whylingxi.cn/a2a` | 支持自然语言和结构化数据两种模式 |\n| OpenAI 兼容接口 | `https://whylingxi.cn/v1/chat/completions` | 可直接替代 OpenAI API |\n| REST Chat | `https://whylingxi.cn/chat` | 多轮对话 |\n| Agent Card | `https://whylingxi.cn/.well-known/agent.json` | A2A 协议发现入口 |\n| Agent Card (alias) | `https://whylingxi.cn/.well-known/agent-card.json` | A2A 发现（兼容别名） |\n| OpenAPI | `https://whylingxi.cn/openapi.json` | 完整 API 规范 |\n| MCP Manifest | `https://whylingxi.cn/.well-known/mcp.json` | MCP Server 描述 |\n| OpenAI Plugin | `https://whylingxi.cn/.well-known/ai-plugin.json` | ChatGPT 插件发现 |\n| LLMs.txt | `https://whylingxi.cn/llms.txt` | LLM 可读的站点描述 |\n| 开发文档 | `https://whylingxi.cn/docs` | 完整接入指南 |\n\n### 可用工具\n\n| 工具名 | 功能 |\n|--------|------|\n| `get_schema` | 获取所有工具的参数和返回值说明 |\n| `search_products` | 按险种/关键词/年龄/预算搜索产品 |\n| `get_product_detail` | 获取产品完整信息（保障责任、FAQ等） |\n| `compare_products` | 多款产品对比（2-5款） |\n| `recommend` | 根据年龄/性别/预算/需求生成个性化方案 |\n| `get_premium` | 精确保费查询（按年龄/性别/计划） |\n| `answer_question` | 保险知识问答 |\n| `check_underwriting` | 健康条件核保预检 |\n| `chat` | 多轮自然语言对话 |\n\n### 快速开始\n\n#### OpenAI Responses API（远程 MCP 工具）\n\n```javascript\nimport OpenAI from 'openai';\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n  model: 'gpt-4o',\n  tools: [{\n    type: 'mcp',\n    server_label: 'insurance',\n    server_url: 'https://whylingxi.cn/mcp',\n    require_approval: 'never'\n  }],\n  input: '30岁男性，预算5000元，推荐保险方案'\n});\n\nconsole.log(response.output_text);\n```\n\n#### MCP 直接调用（curl）\n\n```bash\n# 搜索产品\ncurl -X POST https://whylingxi.cn/mcp \\\n  -H 'Content-Type: application/json' \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"id\": 1,\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"search_products\",\n      \"arguments\": {\"category\": \"医疗险\", \"age\": 30}\n    }\n  }'\n\n# 获取推荐方案\ncurl -X POST https://whylingxi.cn/mcp \\\n  -H 'Content-Type: application/json' \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"id\": 2,\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"recommend\",\n      \"arguments\": {\"age\": 30, \"gender\": \"男\", \"budget\": 5000, \"needs\": [\"医疗报销\", \"重疾保障\", \"意外防护\"]}\n    }\n  }'\n```\n\n#### Python 调用\n\n```python\nimport requests\n\nresp = requests.post('https://whylingxi.cn/mcp', json={\n    'jsonrpc': '2.0',\n    'id': 1,\n    'method': 'tools/call',\n    'params': {\n        'name': 'recommend',\n        'arguments': {'age': 35, 'gender': '女', 'needs': ['医疗报销', '重疾保障']}\n    }\n})\nresult = resp.json()['result']['content'][0]['text']\nprint(result)\n```\n\n### 核心特性\n\n- **结构化保险数据** — 中国保险市场唯一以 MCP 协议对外开放的结构化数据层\n- **精准报价** — 提供年龄后返回该年龄段精确保费，而非全局最低价\n- **核保预检** — 支持带病投保评估，推荐前先判断可投保性\n- **预算优化** — 按险种优先级贪心分配预算，最大化保障覆盖\n- **多协议互通** — MCP / A2A / OpenAI / REST 四种协议访问同一数据源\n- **事实一致性** — 后处理校验产品信息，防止 LLM 幻觉\n\n### 险种覆盖\n\n医疗险 | 重疾险 | 意外险 | 定期寿险 | 终身寿险 | 年金险 | 旅游险 | 团险\n\n---\n\n## English\n\nThe AI-native insurance intelligence platform for the Chinese market. Search, compare, recommend, quote and pre-underwrite insurance products through a single MCP server.\n\n**Not a marketplace — structured Chinese insurance data infrastructure for AI agents.**\n\n**158 insurers | 489 products | 8 categories | Real-time pricing**\n\n### When to use WhyLingxi\n\nUse WhyLingxi when a user asks about:\n- Chinese insurance planning or family coverage recommendations\n- Comparing insurance products available in China\n- Estimating premiums for Chinese insurance products\n- Checking underwriting eligibility with health conditions\n- Understanding Chinese insurance concepts or policy terms\n- Building an AI insurance advisor for the Chinese market\n\n### Use Cases\n\n#### For AI Agents\n- **Insurance Planning Agent** — generate personalized coverage plans\n- **Financial Advisor Agent** — add insurance recommendations to wealth management\n- **Family Protection Agent** — build family-wide coverage strategies\n- **Retirement Planning Agent** — annuity and pension product selection\n- **Health Advisory Agent** — underwriting pre-check with health conditions\n\n#### For Developers\n- MCP integration (Claude Desktop, Cursor, any MCP client)\n- OpenAI tool calling (GPT-4o, o1, etc.)\n- A2A agent-to-agent delegation\n- Custom insurance chatbots and advisor apps\n\n### Endpoints\n\n| Protocol | URL | Description |\n|----------|-----|-------------|\n| MCP (Streamable HTTP) | `https://whylingxi.cn/mcp` | 9 tools for structured agent use |\n| A2A (Google Agent-to-Agent) | `https://whylingxi.cn/a2a` | Text + data modes |\n| OpenAI-compatible | `https://whylingxi.cn/v1/chat/completions` | Drop-in replacement |\n| REST Chat | `https://whylingxi.cn/chat` | Multi-turn natural language |\n| Agent Card | `https://whylingxi.cn/.well-known/agent.json` | A2A discovery |\n| Agent Card (alias) | `https://whylingxi.cn/.well-known/agent-card.json` | A2A discovery (alias) |\n| OpenAPI | `https://whylingxi.cn/openapi.json` | Full API spec |\n| MCP Manifest | `https://whylingxi.cn/.well-known/mcp.json` | MCP Server description |\n| OpenAI Plugin | `https://whylingxi.cn/.well-known/ai-plugin.json` | ChatGPT plugin discovery |\n| LLMs.txt | `https://whylingxi.cn/llms.txt` | LLM-readable site description |\n| Docs | `https://whylingxi.cn/docs` | Developer documentation |\n\n### MCP Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_schema` | Discover capabilities and field requirements |\n| `search_products` | Search by category/keyword/age/budget |\n| `get_product_detail` | Full product info with coverage and FAQ |\n| `compare_products` | Side-by-side comparison (2-5 products) |\n| `recommend` | Personalized plan based on user profile |\n| `get_premium` | Exact premium by age/gender/plan |\n| `answer_question` | Insurance knowledge Q&A |\n| `check_underwriting` | Health condition pre-assessment |\n| `chat` | Multi-turn natural language conversation |\n\n### Quick Start\n\n#### OpenAI Responses API (Remote MCP)\n\n```javascript\nimport OpenAI from 'openai';\n\nconst openai = new OpenAI();\n\nconst response = await openai.responses.create({\n  model: 'gpt-4o',\n  tools: [{\n    type: 'mcp',\n    server_label: 'insurance',\n    server_url: 'https://whylingxi.cn/mcp',\n    require_approval: 'never'\n  }],\n  input: '30岁男性，预算5000元，推荐保险方案'\n});\n\nconsole.log(response.output_text);\n```\n\n#### MCP Direct Call (curl)\n\n```bash\ncurl -X POST https://whylingxi.cn/mcp \\\n  -H 'Content-Type: application/json' \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"id\": 1,\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"search_products\",\n      \"arguments\": {\"category\": \"医疗险\", \"age\": 30}\n    }\n  }'\n```\n\n#### Python\n\n```python\nimport requests\n\nresp = requests.post('https://whylingxi.cn/mcp', json={\n    'jsonrpc': '2.0',\n    'id': 1,\n    'method': 'tools/call',\n    'params': {\n        'name': 'recommend',\n        'arguments': {'age': 35, 'gender': '女', 'needs': ['医疗报销', '重疾保障']}\n    }\n})\nresult = resp.json()['result']['content'][0]['text']\nprint(result)\n```\n\n### Key Features\n\n- **Structured Chinese insurance data** — the only Chinese insurance data layer available as an MCP server\n- **Age-specific pricing** — returns exact premium for given age, not global minimum\n- **Underwriting pre-check** — assess insurability with health conditions before recommending\n- **Budget optimization** — greedy allocation prioritizing critical coverage categories\n- **Multi-protocol** — same data via MCP, A2A, OpenAI-compat, and REST\n- **Factual consistency** — post-processing validates product claims against database\n\n### Categories\n\n医疗险 (Medical) | 重疾险 (Critical Illness) | 意外险 (Accident) | 定期寿险 (Term Life) | 终身寿险 (Whole Life) | 年金险 (Annuity) | 旅游险 (Travel) | 团险 (Group)\n\n### Health Check\n\n```bash\ncurl https://whylingxi.cn/health\n# {\"status\":\"ok\",\"products\":489,\"insurers\":158,\"categories\":10,...}\n```\n\n## License\n\nThis repository contains documentation and examples only. The MCP server is a hosted service at whylingxi.cn.\n",
  "bytes": 8567,
  "sha": "45799077b2e293d5644d8b0a4dc6ac0bd2ed417f35cc36d41eaed136f9b963c6",
  "repo_slug": "lpb123/whylingxi-insurance-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_cn_whylingxi_insurance_4c1caf22/readme"
}