onchain-safety-mcp
MCP serverAI & modelsToken-safety for AI agents: rug/honeypot verdict + score across PulseChain, Monad, Base & BSC
This server has no hosted endpoint yet, so ahel can't serve it. You can still add it. It stays paused until ahel can serve it.
Serve it through your gateway
One link, every agent. Your own credentials, stored once.
Tools it gives your agents (9)
| Tool | What it does |
|---|---|
| check_token_safety | Scam/safe verdict for an ERC-20 token on PulseChain, Monad, Base, or BSC. Returns verdict (SAFE / LOW_RISK / CAUTION / HIGH_RISK / LIKELY_RUG / NOT_A_TOKEN / UNKNOWN), a 0-100 score, confidence, and... |
| fresh_rug_radar | The most recently created liquidity pools, each safety-scored the moment it appeared (verdict, 0-100 score, seconds-since-creation). |
| exit_safety | Can you sell $X of a token at acceptable slippage? Size-aware price-impact check (on-chain reserves + routed quote) plus the safety verdict. |
| check_ownership | Is ownership renounced, is the contract upgradeable (proxy), and what powers can an active owner still use (mint / blacklist / pause / adjust tax)? |
| safe_to_interact | One call before touching a contract: bundles the safety verdict + ownership/privileges into a single recommendation — SAFE_TO_INTERACT / CAUTION / DO_NOT_INTERACT — with reasons. |
| wallet_approvals | Enumerate a wallet's active ERC-20 approvals (allowances granted to spender contracts) and flag the unlimited ones — the classic wallet-drainer vector. Call to audit what could quietly drain a wallet. |
| wallet_poison_check | Scan a wallet's recent incoming transfers for address-poisoning attacks — dust/zero-value transfers from lookalike addresses (first-4+last-4 chars matching a real counterparty the wallet has paid)... |
| wallet_reputation | Counterparty-hygiene read before transacting WITH a wallet: account shape (EOA/contract), history depth, known-rug holdings, and (with a paid key) drainer-approval exposure + address-poisoning... |
| ai_incident_lookup | AI-risk history for a company or vendor: documented AI incidents (3.3K+ from public incident databases), regulatory fines with EUR amounts, and SEC AI-risk disclosures. |
Signals
- Last commit
- Jul 2026
- Tools captured
- 9
ahel review (caution)
S2medium
demands high-sensitivity credentials
Automated review, not a security audit. Ruleset v1.