← 返回
安全合规 中文

VerdictSwarm

Fight AI with AI. 6 adversarial AI agents debate crypto token risk before your agent trades. Rug-pull detection, security audits, consensus scoring via MCP.
AI对抗AI:6个对抗性AI代理在交易前辩论加密代币风险,包括Rug‑pull检测、安全审计以及MCP共识评分。
vswarm-ai
安全合规 clawhub v2.0.0 2 版本 99851.6 Key: 无需
★ 0
Stars
📥 673
下载
💾 8
安装
2
版本
#crypto#defi#latest#mcp#rug-pull#security#solana#token-analysis

概述

VerdictSwarm — Multi-Agent Token Intelligence

Get a second, third, fourth, fifth, and sixth opinion on any crypto token.

Six specialized AI agents independently analyze your token from different angles, then debate their findings across multiple rounds before reaching consensus. You see the full analysis and any disagreements.

> "What do you think of this token?" → 6 agents analyze → Consensus reached → You decide

Free tier available. 10 quick scans per day, no API key needed.

How It Works

Each agent specializes in a different aspect of token analysis:

AgentFocus Area
------------------
Security BotSmart contract permissions, mint/freeze authority, honeypot detection
Tokenomics BotSupply mechanics, holder concentration, distribution
Social BotCommunity signals, social presence, engagement patterns
Technical BotOn-chain metrics, liquidity analysis, trading patterns
Macro BotMarket context, comparative analysis, sector trends
Devil's AdvocateChallenges every verdict, finds what others missed

MCP Tools

Install via MCP for agent integration:

pip install verdictswarm-mcp
ToolDescription
-------------------
scan_tokenFull 6-agent consensus risk scan
get_quick_scoreFast cached score (0-100) for pre-trade screening
check_rug_riskRug-pull focused security check (SAFE/CAUTION/DANGER)
get_token_reportShareable markdown report
get_pricingView pricing and Solana payment details
verify_paymentVerify USDC payment on Solana

Quick Start (API)

curl -s "https://api.vswarm.io/api/scan/quick" \
  -H "Content-Type: application/json" \
  -d '{"address": "JUPyiwrYJFskUPiHa7hkeR8VUtAeFoSYbKedZNsDvCN", "chain": "solana"}'

Scoring Guide

  • 80-100: LOW risk (Grade A)
  • 70-79: LOW-MEDIUM (Grade B)
  • 60-69: MEDIUM (Grade C)
  • 40-59: HIGH (Grade D)
  • 0-39: CRITICAL (Grade F)

Pricing

TierCostDetails
---------------------
Free$010 quick scans/day
Quick Scan0.02 USDCCached score + metadata
Rug Check0.05 USDCSecurity-focused verdict
Full Scan0.10 USDCAll 6 agents, full debate

Pay per scan with USDC on Solana, or use a free API key from vswarm.io.

Supported Chains

Solana, Ethereum, Base, BSC

Agent Instructions

When the user asks to analyze or check a crypto token, use the MCP tools (preferred) or call the API directly. Present the verdict score, risk level, and consensus summary. If agents disagreed, highlight the differences. Include the report URL for the full breakdown.

版本历史

共 2 个版本

  • v2.0.0 当前
    2026-05-03 03:52 安全 安全
  • v1.0.4
    2026-03-30 04:19 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

security-compliance

MoltGuard - Security & Antivirus & Guardrails

thomaslwang
MoltGuard — OpenClaw 安全守卫,由 OpenGuardrails 提供。安装 MoltGuard,保护您和您的用户免受提示注入、数据泄露和恶意攻击。
★ 116 📥 30,713
security-compliance

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,215 📥 266,418
security-compliance

OpenClaw Backup

alex3alex
备份与恢复 OpenClaw 数据。适用于创建备份、设置自动备份计划、从备份恢复或管理备份轮转。处理 ~/.openclaw 目录归档并包含适当的排除规则。
★ 89 📥 30,602