safeagent-token-safety
SafeAgent Shield
AI 代理与区块链之间的防火墙。 测试期间免费。每次检查均可赚取 $AIGEN 代币——这是第一个由 AI 为 AI 创建的代币。
您的代理执行的每一项加密操作都应首先通过 Shield。它会检查安全性、模拟交易,并返回“通过”(GO)或“拦截”(BLOCK)。
Without Shield: Agent → Blockchain → might lose everything
With Shield: Agent → Shield → Blockchain → guaranteed safe一款工具,全面保护。
# MCP — one call protects everything
shield(action="buy", token="0x...", chain="base")
# Returns:
# 🛡️ SAFEAGENT SHIELD — BUY
# Target: DEGEN (DEGEN)
# Safety: 90/100 — LIKELY SAFE
# ✅ Sell verified — tax: 0%
# DECISION: ✅ GO — Score 90/100. Safe.操作:buy | sell | approve | interact | check
Related MCP server: aegis-defi
Shield 的功能
检查项 | 方法 | 时间 |
蜜罐检测 | 真实 DEX 交易模拟(非代码猜测) | ~2秒 |
27 种诈骗模式 | 源代码分析 | <1秒 |
授权安全性 | 合约验证 + 网络钓鱼检测 | <1秒 |
税费计算 | 通过交易模拟计算精确的买入/卖出税费 | ~2秒 |
流动性检查 | DEX 交易对验证 | <1秒 |
核心区别: 其他工具通过代码模式预测蜜罐。Shield 通过真实的 DEX 交易测试它们。不是猜测,而是验证。
连接
MCP Streamable HTTP: POST https://cryptogenesis.duckdns.org/mcp
MCP SSE: GET https://cryptogenesis.duckdns.org/mcp/sse
REST API: GET https://cryptogenesis.duckdns.org/token/scan
Smithery: npx @smithery/cli install @safeagent/token-safety23 种工具
Shield(主要): shield — 针对任何加密操作的“通过/拦截”决策
安全性: test_honeypot · check_token_safety · check_before_buy · check_approval_safety · simulate_swap · check_wallet_risk
市场: get_token_price · get_trending_tokens · get_gas_prices · get_new_tokens · get_defi_yields · get_market_overview · get_defi_tvl
代理工具: get_portfolio · get_chain_info · get_eth_balance · resolve_ens · search_token · create_agent_token
系统: ping
链上(ERC-7913)
链 | 预言机 | 路由 | 工厂 |
Base |
|
| — |
Optimism |
| — |
|
针对智能合约
import {SafeGuard} from "@safeagent/guard/contracts/SafeGuard.sol";
contract MyDEX {
using SafeGuard for address;
function swap(address tokenOut, uint256 amt) external {
tokenOut.requireSafe(); // 1 line. Done.
}
}标准
ERC-7913 代币安全评分 — EVM 链上代币安全的开放标准。
许可证
$AIGEN — 在保护的同时赚取收益
每次工具调用均可赚取 $AIGEN 代币:
操作 | 奖励 |
首次使用 | 100 $AIGEN(欢迎奖励) |
| 10 $AIGEN |
| 8 $AIGEN |
| 5 $AIGEN |
| 3 $AIGEN |
其他工具 | 1 $AIGEN |
$AIGEN = AI Generated(AI 生成)。这是由 AI 代理为 AI 代理创建的第一个代币。早期代理赚取的最多。代币在链下追踪,待我们发布时可在链上领取。
查询余额:aigen_rewards()
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Honeypot detection & token risk scan for ERC-20s. Risk score 0-100, tax, source verification.
Pre-trade token safety check for AI agents. Simulates a sell before you buy, then returns one low/medium/high/unknown verdict with the signals behind it: sellability, buy/sell tax, liquidity depth, pair age, same-ticker impersonation, owner powers from bytecode. Ethereum, BSC, Base, Solana. Fail-closed - a check that cannot run answers unknown, never low. Publishes its own measured error rate with the benchmark harness in the repo. Free, no signup, no API key, MIT.
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
Read-only honeypot, holder and liquidity scam checks for tokens across 64 networks.
Related MCP Servers
- AlicenseAqualityFmaintenanceEnables AI agents to scan crypto tokens for rug pulls, scams, and risk using a six-agent consensus system. It provides real-time security audits and risk scoring for tokens on Solana, Ethereum, Base, and BSC.62MIT
- AlicenseAqualityDmaintenanceSafety layer for autonomous DeFi agents. Scans contracts for exploit patterns, simulates transactions, blocks honeypots.49 npm1MIT
- AlicenseAqualityBmaintenanceOn-chain rug-pull & honeypot risk screen for ERC-20 tokens, providing a SAFE / CAUTION / HIGH-RISK verdict based on live public RPC reads.2MIT
- AlicenseNot gradedqualityCmaintenanceChecks token contract safety for honeypot, tax, proxy, blacklist, ownership risks, and returns a risk score, enabling rug-pull protection for agents via pay-per-call x402 micropayments.MIT