Two pre-trade decisions: should-i-pay + token-verdict. ERC-8004 sybil forensics + live pool checks
Scored across 2 tools
The two tools target genuinely different questions: token risk before a swap vs. counterparty risk before an A2A payment. The descriptions do a good job of drawing the line (on-chain ERC-8004 evidence vs. Bazaar demand data), but the should_i_pay description points to a non-existent 'agent_interact_gate' tool for broader questions, which can leave an agent unsure where that case should go.
Both names are snake_case, but the conventions differ sharply: one is a verb_noun command (check_base_token_safety) and the other is a first-person question (should_i_pay). Readable in isolation, yet there is no predictable pattern an agent can extrapolate a third tool from.
Two tools is thin for a server branding itself 'On-chain AI Agent Intelligence' spanning token safety, agent reputation, and x402 seller trust. Each tool is substantive, but the surface is borderline too small to justify a dedicated server.
There is a clear dead end: should_i_pay defers broader agent questions to 'agent_interact_gate', which is not in this tool set, so that workflow simply fails. Coverage is also asymmetric — payment checks accept Solana targets while token safety only covers Base tokens, and there is no way to inspect an agent's raw ERC-8004 reputation or batch-screen multiple targets.
Is this Base token BASED / MID / COOKED / RADIOACTIVE? Deterministic verdict before you buy: grade, action (ENTER_OK / CAUTION / SKIP), confidence, red flags (honeypot, sell tax, mintable supply, owner privileges, holder concentration, thin liquidity) and expected loss for your amount. Call it before swapping into any Base token. Fail-closed: an unknown token returns UNKNOWN, never "safe". Risk screen, not investment advice. REST: GET|POST /api/v1/token/verdict ($0.02).
Args: token: ERC-20 contract address on Base (0x...) amount_usd: planned position size in USD (scales expected_loss_usd)
Inputs: token (required), amount_usd. Returns: result
Pre-payment decision for any A2A payment: "should I pay this seller $N?". Call it before every payment to an unknown agent or x402 seller — the agent-facing equivalent of a credit check: pay $0.01 to avoid paying a scammer $N. Answers with action PAY / CAUTION / SKIP, confidence and expected loss in USDC sized to your exact amount. Target by ERC-8004 agent_id, Solana pubkey, x402 seller_url or seller pay_to wallet. Agent targets use on-chain ERC-8004 evidence; seller targets use Bazaar demand (repeat payers/calls). For seller targets wallet_flow is marked not_available — demand data does not see seller→payer round trips. Use agent_interact_gate instead when the question is broader than payment. REST: GET /api/v1/should-i-pay ($0.01).
Args: agent_id: ERC-8004 agent id of the payment TARGET (or use another target) solana_asset: Solana 8004 agent pubkey (alternative to agent_id) seller_url: x402 seller resource URL or domain (alternative target) pay_to: seller payTo wallet — EVM 0x… or Solana base58 (alternative target) amount_usd: the USDC amount you are about to pay
Not investment advice.
Inputs: pay_to, agent_id, amount_usd, seller_url, +1 more. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Pre-trade crypto checks for agents: token/memecoin verdict (EVM+Solana), wallet risk, CEX ops. x402.
Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.
Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.
Pre-trade oracle: real slippage, honeypot/sellability at size, exotic DEXs and new chains.
Add one secure layer between your agents and this server.