Agent Guard

Endpoints (12 live)

• POST /v1/wallet/risk-score — Deep risk scoring for a wallet before your agent pays it. Base: contract vs EOA, tx count, ETH balance, USDC balance, vanity patterns, zero/low activity. Solana: recent signatures, SOL balance, USDC token accounts, activity flags. Returns riskScore (0-1), label (low|medium|high|critical), flags[], metrics, and recommendation (safe_to_pay|review|avoid). Designed for agents that need to decide whether to trust a counterparty wallet. (0.025 USDC on Base)
• POST /v1/pii/redact — Mask emails, phone numbers, card numbers, SSNs, and EVM private-key-like hex strings in free text. (0.005 USDC on Base)
• POST /v1/json/repair — Fix trailing commas, single quotes, and unquoted keys — common JSON errors from LLMs. (0.002 USDC on Base)
• POST /v1/scam/scan — Heuristic risk score for seed phrases, urgency scams, fake airdrops, and wallet-drain patterns. (0.005 USDC on Base)
• GET /v1/address/validate — Validate an EVM address (format and checksum style) or a Solana base58 address. (0.003 USDC on Solana)
• GET /v1/address/format-check — Regex-only structural check: confirms 0x + 40 hex characters for EVM, or 32-44 char base58 for Solana. No checksum computed, no RPC call made. Use as a cheap pre-filter before the full checksum check at /v1/address/validate. (0.001 USDC on Base)
• GET /v1/iban/validate — Full ISO 13616 structural check plus ISO 7064 mod-97-10 check-digit verification (the same algorithm banks use). Returns valid (boolean), country code, and the normalized IBAN string. (0.003 USDC on Base)
• GET /v1/iban/format-check — Regex-only structural check: two-letter ISO 3166 country code, two check digits, 10-30 alphanumeric BBAN characters. Mod-97 check digits are NOT computed here. Use as a cheap pre-filter before the full check at /v1/iban/validate. (0.001 USDC on Solana)
• POST /v1/risk/full-scan — One paid call runs any combination of: text (PII redact + scam scan), address+network (deep on-chain wallet risk score), iban (mod-97 validation), and resourceUrl (x402 endpoint reputation check) — whichever fields you include in the JSON body. Returns each sub-result plus one aggregated overallRiskScore/overallLabel. $0.04 total vs calling the tools separately. (0.04 USDC on Base)
• POST /v1/wallet/heuristic-flags — Live JSON-RPC call to a public node — eth_getCode + eth_getTransactionCount on Base, or getSignaturesForAddress on Solana. Reports contract-vs-EOA, on-chain transaction count / recent signature count, and repeated-character vanity-address pattern detection. Lightweight pre-filter. For deeper scoring use /v1/wallet/risk-score. (0.015 USDC on Base)
• POST /v1/x402/endpoint-check — Sends an unauthenticated GET to the given x402 resource URL and checks: does it return HTTP 402, does the accepts[] array include valid payTo/scheme/network/amount fields, is the price under 1.00 USDC, is maxTimeoutSeconds within a normal 5-3600s range, and does /.well-known/x402 exist at the origin. Returns a redFlags array and a 0-1 riskScore — useful before your own agent pays an unfamiliar x402 endpoint. (0.02 USDC on Base)
• GET /v1/iban/validate — Full ISO 13616 structural check plus ISO 7064 mod-97-10 check-digit verification (the same algorithm banks use). Returns valid (boolean), country code, and the normalized IBAN string. (0.003 USDC on Base)

MCP tools (11)

Agent Guard https://agent-guard.annushka1190.workers.dev/mcp

• address_format_check — Structural check of a crypto address. Regex-only structural check: confirms 0x + 40 hex characters for EVM, or 32-44 char base58 for Solana. No checksum computed, no RPC call made. Use as a cheap pre-filter before the full checksum check at /v1/address/validate. Price: $0.001 USDC via x402.
• address_validate — Validate crypto address. EIP-55 mixed-case checksum validation for 0x-prefixed 40-hex-character EVM addresses, or base58 charset/length validation for Solana addresses. Returns valid (boolean), chain (evm|solana), and checksumOk fields. Price: $0.003 USDC via x402.
• iban_format_check — Structural check of an IBAN. Regex-only structural check: two-letter ISO 3166 country code, two check digits, 10-30 alphanumeric BBAN characters. Mod-97 check digits are NOT computed here. Use as a cheap pre-filter before the full check at /v1/iban/validate. Price: $0.001 USDC via x402.
• iban_validate — Validate IBAN. Full ISO 13616 structural check plus ISO 7064 mod-97-10 check-digit verification (the same algorithm banks use). Returns valid (boolean), country code, and the normalized IBAN string. Price: $0.003 USDC via x402.
• json_repair — Repair broken JSON. Parses malformed JSON typically produced by LLM output: strips markdown code fences, removes trailing commas before ]/}, converts single-quoted strings and unquoted object keys to valid double-quoted JSON. Returns the parsed object plus a boolean flag indicating whether a fix was needed. Price: $0.002 USDC via x402.
• pii_redact — Redact PII from text. Detects and masks 5 PII categories in free text via regex: email addresses, phone numbers (8+ digits), card numbers (13-19 digits, Luhn-length), US SSN format (XXX-XX-XXXX), and 64-hex-char strings that match an EVM private key shape. Returns the redacted text plus a per-category match count. Price: $0.005 USDC via x402.
• risk_full_scan — Combined risk report (bundle). One paid call runs any combination of: text (PII redact + scam scan), address+network (deep on-chain wallet risk score), iban (mod-97 validation), and resourceUrl (x402 endpoint reputation check) — whichever fields you include in the JSON body. Returns each sub-result plus one aggregated overallRiskScore/overallLabel. $0.04 total vs calling the tools separately. Price: $0.04 USDC via x402.
• scam_scan — Scam and phishing text scan. Regex-heuristic scan for 7 known crypto-scam patterns: seed-phrase/recovery-phrase requests, gas-fee-in-advance scams, fake wallet-connect airdrop claims, urgency/pressure language, private-key exfiltration requests, unlimited-token-approval drainer patterns, and fake wallet-support impersonation. Returns a 0-1 score, a high/medium/low label, and the list of matched pattern names. Price: $0.005 USDC via x402.
• wallet_heuristic_flags — On-chain wallet heuristic flags (lightweight). Live JSON-RPC call to a public node — eth_getCode + eth_getTransactionCount on Base, or getSignaturesForAddress on Solana. Reports contract-vs-EOA, on-chain transaction count / recent signature count, and repeated-character vanity-address pattern detection. Lightweight pre-filter. For deeper scoring use /v1/wallet/risk-score. Price: $0.015 USDC via x402.
• wallet_risk_score — Deep on-chain wallet risk score. Deep risk scoring for a wallet before your agent pays it. Base: contract vs EOA, tx count, ETH balance, USDC balance, vanity patterns, zero/low activity. Solana: recent signatures, SOL balance, USDC token accounts, activity flags. Returns riskScore (0-1), label (low|medium|high|critical), flags[], metrics, and recommendation (safe_to_pay|review|avoid). Designed for agents that need to decide whether to trust a counterparty wallet. Price: $0.025 USDC via x402.
• x402_endpoint_check — x402 counterparty endpoint reputation check. Sends an unauthenticated GET to the given x402 resource URL and checks: does it return HTTP 402, does the accepts[] array include valid payTo/scheme/network/amount fields, is the price under 1.00 USDC, is maxTimeoutSeconds within a normal 5-3600s range, and does /.well-known/x402 exist at the origin. Returns a redFlags array and a 0-1 riskScore — useful before your own agent pays an unfamiliar x402 endpoint. Price: $0.02 USDC via x402.