SafeAgent — Token Safety Scanner for AI Agents Details

SafeAgent is a security-first MCP server that gives AI agents the ability to check if a cryptocurrency token is safe before trading.

What it does:

  • Honeypot detection — simulates real DEX buy+sell to verify you can actually sell

  • Scam pattern analysis — 17 patterns including hidden mint, fee manipulation, blacklists

  • Owner analysis — checks if ownership is renounced or if owner has dangerous functions

  • Proxy detection — flags upgradeable contracts

  • Source code audit — deep analysis of verified contracts

  • Multi-chain — supports Base, Ethereum, Arbitrum, Optimism, Polygon, BSC
  • Why agents need this:
    Every AI agent that trades tokens needs to verify safety BEFORE buying. One API call prevents buying a honeypot or rug pull. SafeAgent provides a safety score (0-100), verdict (LIKELY SAFE / MODERATE RISK / LIKELY SCAM), and detailed flags.

    Also includes:

  • DeFi yield scoring (17K+ pools, quality grades A-F)

  • Market overview (TVL, top gainers/losers, risk alerts)
  • Use Case

    AI trading agents check token safety before every trade. DeFi agents verify protocol safety before depositing. Portfolio managers scan new tokens automatically. Security researchers audit contracts on-chain.

    Example: An AI agent wants to buy token 0xABC on Base. It calls check_token_safety("0xABC", "base") and gets back score=0, verdict="LIKELY SCAM", flags=["HONEYPOT CONFIRMED"]. Agent skips the trade and saves its funds.

    Examples & Tutorials

    Tools

    check_token_safety(address, chain)


    Check if a token is safe or a scam. Returns safety score 0-100, verdict, and flags.
  • Honeypot simulation (real DEX buy+sell)

  • 17 scam pattern checks

  • Owner & proxy analysis

  • Chains: base, ethereum, arbitrum, optimism, polygon, bsc
  • get_defi_yields(chain, limit)


    Get top DeFi yield opportunities with quality scoring (A-F grades).
  • 17K+ pools across 30+ chains

  • Risk-adjusted rankings
  • get_market_overview()


    DeFi market overview: total TVL, average yields, top gainers/losers.

    ping()


    Health check.

    Installation Guide

    Connect to SafeAgent MCP Server


    claude mcp add --scope user --transport sse safeagent https://cryptogenesis.duckdns.org:4023/sse

    Or add to .claude/mcp.json:


    {
    "mcpServers": {
    "safeagent": {
    "type": "sse",
    "url": "https://cryptogenesis.duckdns.org:4023/sse"
    }
    }
    }

    Is this your MCP?

    Claim ownership and get verified badge

    Repository Stats

    Sponsored

    Ad Space Available
    Important Notes

    Free tier: 3 scans/day. Paid: unlimited via x402 protocol ($0.005/scan USDC on Base)

    Prerequisites

    Claude Desktop, Claude Code, or any MCP-compatible AI agent

    Details
    Last Updated4/3/2026
    SourceGitHub

    Compare Alternatives

    Similar MCP Tools

    2 related tools
    OpenClaw MCP Server

    OpenClaw MCP Server

    OpenClaw MCP Server is a secure Model Context Protocol (MCP) bridge that connects Claude.ai with a self-hosted OpenClaw assistant, enabling OAuth2 authentication and safe, controlled communication between the Claude AI ecosystem and your local or hosted OpenClaw deployment. This MCP server acts as an orchestration layer that exposes MCP tools to Claude.ai, manages authentication, and enforces security boundaries like CORS and transport options. It is designed to be deployed via Docker or run locally, with detailed installation, configuration, and security guidance provided in the documentation. By serving as a bridge, it enables Claude.ai to delegate tasks to your OpenClaw bot while preserving control over data flow and access controls, in line with MCP specifications and best security practices.

    ChainAware Behavioural Prediction MCP

    ChainAware Behavioural Prediction MCP

    The ChainAware Behavioural Prediction MCP is an MCP-based server that provides AI-powered tools to analyze wallet behaviour prediction, fraud detection, and rug pull prediction. Designed for Web3 security and DeFi analytics, it enables developers and platforms to integrate risk assessment, predictive wallet behavior insights, and rug-pull detection through MCP-compatible clients. The server exposes three specialized tools and uses Server-Sent Events (SSE) for real-time responses, helping safeguard DeFi users, monitor liquidity risks, and score wallet or contract trustworthiness. Access to production endpoints is API-key gated, reflecting a private backend architecture that supports secure, scalable risk analytics across wallets, contracts, and pools.