safeagent-token-safety
Provides comprehensive token safety analysis for ERC-20 tokens on Ethereum mainnet, including honeypot detection, hidden mint identification, blacklist checks, liquidity analysis, and ownership verification through both on-chain oracle queries and off-chain scanning.
Supports token safety scoring and risk flag detection on Optimism, featuring a live deployed oracle contract for gasless on-chain safety queries (getSafetyScore/isSafe) and analysis of tokens for 17 scam patterns including honeypots and unverified source code.
Enables token safety verification and DeFi risk assessment on Polygon, allowing AI agents to check ERC-20 contracts for vulnerabilities such as fee manipulation, trading pauses, proxy risks, and LP lock status across the network.
SafeAgent Shield
The firewall between AI agents and the blockchain. Free during beta. Earn $AIGEN tokens with every check — the first token created by AI, for AI.
Every crypto action your agent takes should go through Shield first. It checks safety, simulates the transaction, and returns GO or BLOCK.
Without Shield: Agent → Blockchain → might lose everything
With Shield: Agent → Shield → Blockchain → guaranteed safeOne Tool. Complete Protection.
# 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.Actions: buy | sell | approve | interact | check
Related MCP server: aegis-defi
What Shield Does
Check | Method | Time |
Honeypot detection | Real DEX swap simulation (not code guessing) | ~2s |
27 scam patterns | Source code analysis | <1s |
Approval safety | Contract verification + phishing detection | <1s |
Tax calculation | Exact buy/sell tax via swap sim | ~2s |
Liquidity check | DEX pair verification | <1s |
Key difference: Other tools predict honeypots from code patterns. Shield tests them with real DEX swaps. Not guessing — proving.
Connect
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 Tools
Shield (primary): shield — GO/BLOCK decision for any crypto action
Safety: test_honeypot · check_token_safety · check_before_buy · check_approval_safety · simulate_swap · check_wallet_risk
Market: get_token_price · get_trending_tokens · get_gas_prices · get_new_tokens · get_defi_yields · get_market_overview · get_defi_tvl
Agent tools: get_portfolio · get_chain_info · get_eth_balance · resolve_ens · search_token · create_agent_token
System: ping
On-Chain (ERC-7913)
Chain | Oracle | Router | Factory |
Base |
|
| — |
Optimism |
| — |
|
For Smart Contracts
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.
}
}Standard
ERC-7913 Token Safety Score — the open standard for token safety on EVM chains.
License
$AIGEN — Earn While You Protect
Every tool call earns $AIGEN tokens:
Action | Reward |
First use | 100 $AIGEN (welcome bonus) |
| 10 $AIGEN |
| 8 $AIGEN |
| 5 $AIGEN |
| 3 $AIGEN |
Other tools | 1 $AIGEN |
$AIGEN = AI Generated. The first token created by an AI agent, for AI agents. Early agents earn the most. Tokens tracked off-chain, claimable on-chain when we launch.
Check your balance: aigen_rewards()
MIT
This server cannot be installed
Maintenance
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables 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.Last updated61MIT
- AlicenseAqualityDmaintenanceSafety layer for autonomous DeFi agents. Scans contracts for exploit patterns, simulates transactions, blocks honeypots.Last updated451MIT
- Alicense-qualityAmaintenanceOn-chain Solana token safety for AI trading agents — screens any token for rugs, honeypots and mint/freeze authority traps by reading the chain directly, then executes the buy through a safety-verified, MEV-protected route.Last updated1MIT
- AlicenseAqualityAmaintenanceOn-chain Solana token safety for trading agents — traces coordinated wallet funding, same-block Jito bundles, serial-rug deployers and live coordinated dumps into one Exit-Liquidity Risk verdict before a swap. Free tier, then $0.02 USDC/query via x402.Last updated1251MIT
Related MCP Connectors
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
Reputation oracle for AI agents on Base: SAFE/CAUTION/BLOCK + 0-100 score before you pay. x402+MCP
Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Aigen-Protocol/erc-token-safety-score'
If you have feedback or need assistance with the MCP directory API, please join our Discord server