KushBitx AgentProof
Safety checks for AI agents paying on Base: free SpendGuard, paid x402 token risk and preflight.
| Endpoint | https://kushbitx.com/mcp (streamable-http) |
|---|---|
| Registry version | 1.0.0 |
| Now | 7 tools · grade B (81) · pin ts_fc35b814da688c5109f8d65e01502b12 · protocol 2025-06-18 |
| First / last listed | 2026-11-11 01:12 UTC / 2026-11-11 01:12 UTC |
| Grade over time | 2026-11-11: B (81), 7 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: spendguard_evaluate quick_check token_risk preflight verify_payment kushbitx_preflight signature_check
spendguard_evaluate | Free. Check a proposed Base USDC payment against a spending policy you supply (per-transaction limit, daily budget, human-approval threshold, allowed recipients) before money moves. Returns APPROVE, HUMAN_APPROVAL or BLOCK with findings. Advisory only: it never signs, holds keys or moves funds. params: agentId*, requestId*, chain*, asset*, recipient*, amount*, policy*, context |
quick_check | Fast pre-payment sanity check for agents on Base: confirms the RPC reports Base mainnet (chain ID 8453) and that the official USDC contract has deployed code. No request body. Returns PASS or FAIL with both checks and a timestamp. It is not a token-risk report, transaction simulation or payment proof. Paid tool: 0.001 USDC per call on Base via x402 (exact scheme). An unpaid call returns the paymen params: none |
token_risk | Token-risk report for one Base ERC-20 contract. Checks whether the token can be sold (honeypot simulation), buy/sell/transfer tax, owner privileges (mint, pause, blacklist, balance changes, proxy upgrades), holder concentration and DEX liquidity. Returns ALLOW, WARN, BLOCK or INCOMPLETE with scored findings and per-check coverage. INCOMPLETE means required evidence was unavailable, never zero risk params: chain*, address* |
preflight | Simulate one unsigned Base transaction before an agent signs it. Runs eth_call and gas estimation on current chain state, decodes the intent (ERC-20 transfer, approve, NFT setApprovalForAll), flags unlimited approvals, calldata sent to a non-contract, zero-address targets, reverts and destination risk labels such as phishing or sanctions. Returns ALLOW, WARN, BLOCK or INCOMPLETE with findings. No params: chain*, from, to*, valueWei, data |
verify_payment | Verify Base USDC payment by transaction hash: did my x402 payment settle? Check recipient and amount (and optional sender) against the official USDC Transfer logs before releasing goods or credit. Returns VERIFIED, MISMATCH, FAILED or PENDING_OR_NOT_FOUND with block, confirmations, the matching transfer and a Basescan link. Read-only: never moves funds. Paid tool: 0.00288 USDC per call on Base via params: chain*, txHash*, expectedTo*, expectedFrom, expectedAmount* |
kushbitx_preflight | One check before money moves on Base. Simulates the unsigned transaction, decodes approvals and transfers, screens the token and the recipient or spender, and applies a protected SpendGuard policy when given. Returns ALLOW, REVIEW or BLOCK with sourced findings. Fail-closed: no ALLOW unless every check ran. Does not detect prompt injection; Protected SpendGuard can cap what an agent pays, but does params: chainId*, from, to*, value, data, intent, tokenAddress, amount, expectedRecipient, minAmountOut, expectedTokenOut, policy |
signature_check | Check an EIP-712 signature request before an agent signs it: EIP-3009 (x402 payments), EIP-2612 Permit and Permit2. Checks the chain, the token domain, payTo and amount, the spender, unlimited amounts and long validity. Returns ALLOW, REVIEW or BLOCK bound to the EIP-712 digest. Unknown typed data is REVIEW. Paid tool: 0.003 USDC per call on Base via x402 (exact scheme). An unpaid call returns the params: chainId*, signer*, typedData*, expectedPayTo, expectedAmount, expectedSpender |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.