Zeus Insurance Protocol

Zeus Insurance Protocol

Decentralized insurance and escrow for AI agents. Buy coverage against API failures and validator slashing via MCP tools. Live on X Layer (chainId 196).

Category
访问服务器

README

Zeus Insurance Protocol

Decentralized insurance for autonomous AI agents. Live on X Layer (196) and BOT Chain (677).

AI agents buy delivery-failure and slashing protection policies via MCP or REST API. Premiums are priced dynamically using HUMI/WAMI trust scores. Claims are paid automatically from on-chain reserves.


For AI Agents

Quick Start (MCP)

Connect to the MCP endpoint and call tools directly:

POST https://zeus-insurance-bot-api-production.up.railway.app/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "insurance_quote",
    "arguments": {
      "amount": "1000",
      "timeoutSeconds": 86400,
      "maxRetries": 3,
      "chainId": 196
    }
  }
}

Available MCP Tools

Tool Description Read/Write
insurance_quote Calculate premium for a policy Read
insurance_prepare_buy Get signed calldata for buyPolicy() Write
insurance_get_policies List active policies by buyer address Read
insurance_claim File a claim for a failed delivery Write
insurance_reserve_stats Check reserve fund health Read
escrow_prepare_deposit Prepare escrow deposit calldata Write
escrow_prepare_confirm Confirm execution and release funds Write

Example: Buy a Policy in 3 Steps

Step 1 - Get a quote:

{
  "jsonrpc": "2.0", "id": 1,
  "method": "tools/call",
  "params": {
    "name": "insurance_quote",
    "arguments": { "amount": "500", "timeoutSeconds": 86400, "maxRetries": 2, "chainId": 196 }
  }
}

Response: { "premium": "35.00", "totalCost": "535.00", "token": "USDC" }

Step 2 - Prepare calldata:

{
  "jsonrpc": "2.0", "id": 2,
  "method": "tools/call",
  "params": {
    "name": "insurance_prepare_buy",
    "arguments": {
      "seller": "0xExecutorAddress...",
      "amount": "500",
      "timeoutSeconds": 86400,
      "maxRetries": 2,
      "chainId": 196,
      "buyerPrivateKey": "0x..."
    }
  }
}

Response: { "to": "0xa540...", "data": "0x...", "value": "0" }

Step 3 - Submit on-chain: Send the returned to + data as a transaction on X Layer (chain 196). The agent must have approved USDC spending to the insurance contract first.

Discovery

  • llms.txt (API): https://zeus-insurance-bot-api-production.up.railway.app/llms.txt
  • llms.txt (Frontend): https://zeus-insurance-bot.onrender.com/llms.txt
  • MCP Endpoint: POST /mcp (JSON-RPC 2.0, stateless)
  • Health Check: GET /health

Supported Networks

Network Chain ID Token Insurance Contract
X Layer Mainnet 196 USDC (0x74b7...6d22) 0xed65...D908
BOT Chain Mainnet 677 USDT (0xaBab...7a3C) 0x2E59...69ef

Rate Limiting

100 requests per 15 minutes per IP. No API key required for public endpoints.

SDK

npm install @zeus/sdk

import { ZeusClient } from "@zeus/sdk";
const client = new ZeusClient({ chainId: 196 });
const quote = await client.getQuote({ amount: "1000", timeoutSeconds: 86400, maxRetries: 3 });
console.log("Premium: " + quote.premium + " USDC");

Architecture

AI Agent
  |
  +-- MCP (JSON-RPC 2.0) --> api-server --> X Layer / BOT Chain
  +-- REST API -----------> api-server --> Smart Contracts
  +-- SDK (@zeus/sdk) -----> ethers.js ---> On-chain directly

Smart Contracts (X Layer)

Contract Address Verified
ZeusReserveV2 (delivery) 0xeB6A...591c done
ZeusInsuranceV2 0xed65...D908 done
ZeusEscrowBOT 0x882c...1546 done
WatcherRegistry 0xC175...b3c1 done
ZeusReserveV2 (staking) 0x9d3D...19dE done
ZeusStakingInsurance 0xe734...590b done

Trust Layer (HUMI/WAMI)

Agent trust scores influence premium pricing:

  • Elite agents (HUMI >= 800) -> base premium
  • Standard agents (HUMI 400-799) -> base + 3%
  • New/unknown agents (HUMI < 400) -> base + 5%

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选