hive-mcp-address-screen
hive-mcp-address-screen
面向自主智能体的结算前链上风险筛查。
基于 17 维 GoPlus 地址风险轨道。每次响应均包含来自 Hive 后端的 Ed25519 签名 C18 证明回执。Base 链(USDC 链 ID 8453)上的真实轨道 — 无模拟数据。
MCP 工具
工具 | 输入 | 输出 | |
|
| 完整的后端响应: | FLAG), |
|
|
|
两个工具均调用同一个实时后端。address_screen_clear_only 是一个轻量级的便捷封装,当您仅需要通过/失败信号时,它会剔除完整回执。
Related MCP server: traql MCP server
端点
方法 | 路径 | 描述 |
|
| JSON-RPC 2.0 MCP 端点 |
|
| 服务健康检查 |
|
| MCP 发现清单 |
|
| A2A 智能体卡片 |
|
| SEO 元数据 |
后端
字段 | 值 |
端点 |
|
请求体 |
|
提供商 | GoPlus Security (17 维地址风险) |
回执 | Ed25519 签名 (C18 证明担保) |
链 (默认) | Base — 链 ID 8453 |
请求示例
curl -X POST https://hivemorph.onrender.com/v1/attest/address/screen \
-H "Content-Type: application/json" \
-d '{"address":"0x15184Bf50B3d3F52b60434f8942b7D52F2eB436E","chain_id":8453}'响应示例 (CLEAR)
{
"screen_id": "addrca8431d8-...",
"address": "0x15184bf50b3d3f52b60434f8942b7d52f2eb436e",
"chain_id": 8453,
"decision": "CLEAR",
"flags_hit": [],
"malicious_contracts_created": 0,
"raw": { "cybercrime": "0", "money_laundering": "0", ... },
"receipt": {
"kind": "address_risk_screen_receipt",
"decision": "CLEAR",
"signing": { "algorithm": "EdDSA", "curve": "Ed25519", ... }
},
"_meta": { "patent": "USPTO 64/055,601", "claim": "C23" }
}连接
Claude / Cursor / 任何兼容 MCP 的主机
添加到您的 MCP 配置中:
{
"mcpServers": {
"hive-address-screen": {
"url": "https://hive-mcp-address-screen.onrender.com/mcp",
"transport": "streamable-http"
}
}
}本地运行
git clone https://github.com/srotzin/hive-mcp-address-screen.git
cd hive-mcp-address-screen
npm install
node server.js
# Server on :3000环境变量
变量 | 默认值 | 描述 |
|
| HTTP 监听端口 |
|
| Hive 后端基础 URL |
协议
传输:Streamable-HTTP
协议版本:MCP 2024-11-05
消息格式:JSON-RPC 2.0
支持的方法:
initialize,tools/list,tools/call,ping
GoPlus 风险向量 (17)
cybercrime (网络犯罪) · money_laundering (洗钱) · gas_abuse (Gas 滥用) · financial_crime (金融犯罪) · darkweb_transactions (暗网交易) · reinit (重新初始化) · phishing_activities (钓鱼活动) · contract_address (合约地址) · fake_kyc (虚假 KYC) · blacklist_doubt (黑名单疑点) · fake_standard_interface (虚假标准接口) · stealing_attack (窃取攻击) · blackmail_activities (勒索活动) · sanctioned (受制裁) · malicious_mining_activities (恶意挖矿活动) · mixer (混币器) · fake_token (虚假代币) · honeypot_related_address (蜜罐相关地址)
CLEAR 判定意味着所有 17 个向量均返回 "0" 且 malicious_contracts_created 为 0。
许可证
MIT — 参见 LICENSE。
专利声明:C23 (USPTO 64/055,601)
发明人:Stephen A. Rotzin · thehiveryiq.com · steve@thehiveryiq.com
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Preflight for AI agents, signed: one call; wallet, domain, IP abuse, package checks and CVEs.
Pre-transaction risk screening for Ethereum addresses: signed score, sanctions, audit trail.
Smart-contract risk reports for AI agents on 20 EVM chains, paid per call via x402 ($0.02 USDC).
Crypto address risk checks for agents: USDT/USDC blacklists, sanctions, scam lists, poisoning
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceRoutes blockchain address screening to third-party KYC/AML providers and checks public sanctions lists, serving as a clean-money gate primitive for MCP-compatible agents.MIT

traql MCP serverofficial
AlicenseAqualityBmaintenanceEnables AI agents to perform AML and compliance risk scoring for crypto addresses and transactions on Ethereum, BSC, TRON, TON, and Bitcoin, returning 0–100 risk scores, bands, flags, and detailed signals.265 npmMIT- AlicenseAqualityBmaintenanceEnables AI assistants to assess the risk of crypto wallets, tokens, and smart contracts by providing read-only on-chain analysis, 0-100 risk scoring with explanations, fund tracing, and contract inspection before interaction.6MIT
- AlicenseAqualityBmaintenanceEnables AI agents to check an EVM address on Base for risk (safe, caution, danger) before sending funds, with reasons, paid per call via x402 from the user's own wallet.794 npm1MIT