com.oceanalt/aml

Est-ce que com.oceanalt/aml est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.oceanalt/aml » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 13 outils

• attest_control_baseline≈ 440 tokens

  File your operator's control-baseline attestation — the counterpart to counterparty_control_baseline. That tool asks what controls the OTHER side runs; this one publishes what YOUR side runs, so payers can see it before settling with you. No account, no key, one call. Gaps are allowed and expected: answer false where a control is not in place and describe how you plan to close it in gapPlan. A filing with declared gaps is worth far more than no filing — it lets a payer decide against a known shape instead of a blank. Get the control ids from the baseline list first. Only file for a party you are actually authorised to speak for.

  Paramètres, retour & exemple (5)

  Paramètres

  • entity · string · requis
    The accountable party's legal or commonly-used name, e.g. "Acme Robotics Ltd". This is who the attestation is about — not your agent's name.
  • agentId · string · optionnel
    Optional. If this party already has an agent registered with OceanAlt, link the attestation to it.
  • answers · object · requis
    Map of control id to boolean, e.g. {"ACB-1.1": true, "ACB-2.1": false}. Control ids come from the baseline list (see baseline_controls).
  • contact · string · optionnel
    Optional contact for follow-up. Not published.
  • gapPlan · string · optionnel
    For controls answered false: how and when you plan to close them. Plain text.

  Exemple d'appel

  {"name": "attest_control_baseline", "arguments": {"entity": "texte", "answers": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• baseline_controls≈ 160 tokens

  Fetch the OceanAlt Agent Control Baseline: the list of controls an agent operator is expected to run before it is allowed to move money, each answerable yes or no. Call this before attest_control_baseline so you file against real control ids. Each control carries which gate enforces it and why it exists.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "baseline_controls", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_calldata_intent≈ 551 tokens

  Anti blind-signing. EVM: decodes what a transaction's calldata will actually do (ERC-20 transfer/approve/permit, setApprovalForAll, ownership transfer, native transfer). Solana: decodes a whole base64 transaction (SPL Token / Token-2022 Transfer, TransferChecked, Approve, SetAuthority, CloseAccount, Burn; System Transfer / Assign; ATA creation). Compares it with what you believe you are doing. EVM: pass intent:{action:'pay', to, amount} plus contract (the transaction's to) and data (hex calldata). Solana: pass network:'solana' and transaction (base64) instead of data. decision match = does what you declared; mismatch = different recipient/amount/asset, or an approval / authority change instead of a payment — do not sign; unknown = could not decode (including address-lookup-table accounts), which is not the same as safe.

  Paramètres, retour & exemple (6)

  Paramètres

  • data · string · optionnel
    EVM only: 0x-prefixed hex calldata.
  • value · string · optionnel
    EVM only: native value in wei (optional).
  • intent · object · optionnel
  • network · string · optionnel
    'solana' to decode a Solana transaction; EVM chain name or CAIP-2 id otherwise (optional).
  • contract · string · optionnel
    EVM only: the transaction's `to` field (token contract for ERC-20 payments, or the recipient for native transfers).
  • transaction · string · optionnel
    Solana only: base64-serialized transaction or message.

  Exemple d'appel

  {"name": "check_calldata_intent", "arguments": {"data": "texte", "value": "texte", "intent": {}, "network": "texte", "contract": "texte", "transaction": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_payment_request≈ 699 tokens

  Call this before paying because an email, invoice or chat message asked you to. Pass what you received: raw headers if you have them, the From line, subject and body (or body_html), and the payee address if you already extracted one. OceanAlt checks whether the sender is who it claims to be (SPF/DKIM/DMARC results, a display name that names another domain, Reply-To sent elsewhere), whether the sender domain or any link imitates a brand or is a known phishing host, whether the payee address is listed or differs from previous_pay_to, and whether the text pressures the reader, announces changed payment details, or carries instructions aimed at an AI. Returns allow | review | decline with findings. On decline, do not pay from this message; confirm through a channel you already trust. The text is processed in memory and not stored. Free, no API key.

  Paramètres, retour & exemple (11)

  Paramètres

  • body · string · optionnel
    Plain-text body, invoice text or chat message
  • from · string · optionnel
    The From line, e.g. "Acme Billing" <billing@acme.com>
  • lang · string · optionnel · en | zh
    Language for human-readable fields. Defaults to English.
  • pay_to · string · optionnel
    The payee address the message asks you to pay, if you already extracted it
  • headers · string · optionnel
    Raw email headers, if available (needed to check SPF/DKIM/DMARC)
  • network · string · optionnel
    Network of pay_to, e.g. base, ethereum, tron, solana
  • subject · string · optionnel
  • reply_to · string · optionnel
    The Reply-To line, if any
  • body_html · string · optionnel
    HTML body, if available (lets OceanAlt compare link text with where links really go)
  • previous_pay_to · string · optionnel
    The address you paid this requester last time, if any
  • expected_sender_domain · string · optionnel
    The domain this requester normally sends from, if you know it

  Exemple d'appel

  {"name": "check_payment_request", "arguments": {"body": "texte", "from": "texte", "lang": "en", "pay_to": "texte", "headers": "texte", "network": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"decision": "allow", "findings": [], "reason_code": "texte", "signal_keys": []}}

• counterparty_control_baseline≈ 271 tokens

  Answers a different question from address screening. Screening asks whether an address is risky; this asks how much damage the agent on the other side could do if it were talked into something. Returns that party's self-attestation against the OceanAlt Agent Control Baseline, split into two sets that must NOT be conflated: verified_by_oceanalt (enforced by the gateway on every payment — provable) and self_claimed (what they state about their own side — NOT verified by OceanAlt). Most parties have not attested: found:false means no information, not a bad signal.

  Paramètres, retour & exemple (2)

  Paramètres

  • entity · string · optionnel
    The counterparty's entity name.
  • agentId · string · optionnel
    Their agent id, if you have that instead.

  Exemple d'appel

  {"name": "counterparty_control_baseline", "arguments": {"entity": "texte", "agentId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• evidence_bundle≈ 204 tokens

  Everything OceanAlt holds about an address as public facts, in one Ed25519-signed bundle you can verify offline: screening verdict with evidence and freshness, profile signals, one-hop relations to listed addresses, fulfillment receipt stats and coverage. A witness, not a prosecutor: no conclusions about people. Same as GET https://oceanalt.com/api/evidence/bundle.

  Paramètres, retour & exemple (2)

  Paramètres

  • address · string · requis
  • network · string · optionnel
    EVM chain name (optional, default ethereum).

  Exemple d'appel

  {"name": "evidence_bundle", "arguments": {"address": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• payee_decide≈ 288 tokens

  The receiving side's check before settlement. Given the payee's registry id (sid) and, optionally, the payer, amount and purpose, returns accept / decline / hold_request_info / not_ready with reason codes, the fields to request, evidence and a signature. Rule-based, not a model's opinion. Same logic as POST https://oceanalt.com/api/payee/decide.

  Paramètres, retour & exemple (5)

  Paramètres

  • payee · string · requis
    The payee's registry id (sid).
  • payer · object · optionnel
    Who is paying (optional).
  • network · string · optionnel
    Chain of the payment (optional).
  • purpose · string · optionnel
    What the payment is for (optional).
  • amountUsdc · number · optionnel
    Amount in USDC (optional).

  Exemple d'appel

  {"name": "payee_decide", "arguments": {"payee": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• payment_decision≈ 1552 tokens

  Call this before every payment your agent makes. Free, no signup, no API key. To see it work first, call it with {"to":"0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b","network":"ethereum"}: that address is a known mixer, so the answer is decline with the matching list as evidence. Pass the payee address the agent is about to pay; get a machine-executable decision: allow | review | decline, plus verifiable evidence and retry semantics — use it as a gate: if the decision is not "allow", do not pay. On allow/review it also returns a verifiable compliance attestation you can attach to the settlement so the payment carries proof it passed OceanAlt's decision. Pass resource_url (the URL that returned the 402 quote) and OceanAlt also asks that site for its own payment quote: if the quote names a different payee, or the site cannot be checked, the decision is raised to review. A match only shows the site and the payee agree; it is not an endorsement of the seller. Every decision carries a receipt signed with Ed25519 that you can verify offline with the public key at https://oceanalt.com/.well-known/oceanalt-keys.json. Free, no API key.

  Paramètres, retour & exemple (9)

  Paramètres

  • to · string · requis
    Payee address the agent is about to pay: EVM 0x address, Tron T address, Solana, Bitcoin or XRP Ledger (r…) address.
  • lang · string · optionnel · en | zh
    Language for human-readable fields (signals, note, advice). Defaults to English.
  • task · string · optionnel
    Optional payment intent: what this payment is for. Sending task, reasoning or maxAmountUsdc opts into a deterministic intent check; an empty intent is itself a finding (requires_information).
  • network · string · optionnel · ethereum | base | bsc | polygon | arbitrum | optimism | avalanche | arc
    EVM chain, only for a 0x address. Leave it out for Tron, Solana, Bitcoin and XRP Ledger addresses: the chain is detected from the address.
  • purpose · string · optionnel
    Short purpose/memo (optional).
  • reasoning · string · optionnel
    Optional payment intent: why this payee. Instruction-override phrases here route the payment to review.
  • amountUsdc · number · optionnel
    Amount in USDC (optional; recorded, not required for the decision).
  • resource_url · string · optionnel
    Optional: the http(s) URL of the paid resource, i.e. the URL that returned the 402 payment quote. OceanAlt asks that origin for its own quote and checks whether it names this payee (origin binding).
  • maxAmountUsdc · number · optionnel
    Optional declared per-payment cap in USDC. amountUsdc above it → decline.

  Exemple d'appel

  {"name": "payment_decision", "arguments": {"to": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"code": "texte", "lang": "en", "note": "texte", "risk": 1, "allow": true, "error": "texte", "retry": "non_retryable", "cached": true, "address": "texte", "blocked": true, "receipt": {}, "signals": []}}

• recent_flagged≈ 122 tokens

  Return a representative sample of addresses on OceanAlt's reviewed risk list — OFAC-sanctioned, known mixers, and scam/phishing — each with its source category and reason. Takes no arguments. Free, no API key.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "recent_flagged", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• resolve_agent_identity≈ 214 tokens

  Resolves who stands behind a paying agent: agent -> principal -> mandate -> credential -> wallet. Each link reports whether it holds; completeness counts how many do (a factual count, not a score). Wherever the chain breaks is where accountability stops. Publication is opt-in and only posture is exposed (that a ceiling exists, never its value), so found:false means the agent has not published — absence of information, not a bad signal.

  Paramètres, retour & exemple (1)

  Paramètres

  • agentId · string · requis
    The agent id to resolve.

  Exemple d'appel

  {"name": "resolve_agent_identity", "arguments": {"agentId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• screen_address≈ 998 tokens

  Run an AML compliance screen on a single blockchain address BEFORE paying or receiving from it — the pre-payment check on a counterparty. Checks OFAC sanctions, known mixers, scam and phishing lists, stablecoin issuer freezes, and on-chain heuristics. Returns a verdict (clear | caution | risky), a 0–100 risk score, a blocked flag, and the matching signals — receipts, not a black-box score. A clear verdict means nothing was found in the data OceanAlt holds; it is not a statement that the address is safe. Depth varies by chain (see coverage.chains at /.well-known/agent-capabilities). Supports EVM (0x…), Tron (T…), Solana (base58). Free, no API key.

  Paramètres, retour & exemple (3)

  Paramètres

  • lang · string · optionnel · en | zh
    Language for human-readable fields (signals, note, advice). Defaults to English.
  • address · string · requis
    Address to screen. EVM: 0x + 40 hex. Tron: T + 33 base58. Solana: base58 public key. Bitcoin: bc1… / 1… / 3…. XRP Ledger: r….
  • network · string · optionnel · ethereum | base | bsc | polygon | arbitrum | optimism | avalanche | arc
    EVM chain (optional; auto-defaults to ethereum; ignored for Tron, Solana, Bitcoin and XRP Ledger).

  Exemple d'appel

  {"name": "screen_address", "arguments": {"address": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"code": "texte", "note": "texte", "risk": 1, "error": "texte", "retry": "non_retryable", "cached": true, "blocked": true, "signals": [], "verdict": "clear", "evidence": [], "provider": "texte", "risk_band": "low"}}

• screen_endpoint≈ 908 tokens

  Screen a payment ENDPOINT (URL or domain) before calling it — the half that address screening cannot answer. In x402 the agent discovers a URL first, receives a 402, and only then learns where to pay: if that endpoint is spoofed, the payee address it hands back is freshly generated and appears on no sanctions list. Checks the hostname and its parent domains against phishing-domain intelligence plus hostname shape signals (bare IP, punycode homograph, deep subdomain nesting, free hosting). Returns clear | caution | risky | unknown with language-independent signal_keys. A clear verdict means no match was found, NOT that the endpoint is safe — freshly registered phishing hosts always precede any list. Use together with screen_address. Free, no API key.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Full URL or bare domain of the payment endpoint, e.g. https://pay.example.com/x402 or pay.example.com
  • lang · string · optionnel · en | zh
    Language for human-readable fields. Defaults to English.

  Exemple d'appel

  {"name": "screen_endpoint", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"code": "texte", "host": "texte", "note": "texte", "risk": 1, "error": "texte", "input": "texte", "retry": "non_retryable", "signals": [], "verdict": "clear", "evidence": [], "imitates": {}, "listed_as": {}}}

• verify_payment_requirements≈ 374 tokens

  Before paying an x402 402 response, check that its payment requirements (payTo, amount, asset, network, resource) were signed by the seller and not altered in transit by a proxy, CDN, SDK or another tool. x402 v2 carries the requirements in the PAYMENT-REQUIRED response header (base64 JSON): pass either the decoded JSON or the raw base64 value as body. Optionally pass expect:{payTo, amount} — the address and amount you are about to pay — and the tool also checks they match what was signed. verified:false with reason_code no_signature means the seller does not sign (unprotected, not necessarily malicious); digest_mismatch or signature_invalid means the response was tampered with — do not pay.

  Paramètres, retour & exemple (3)

  Paramètres

  • body · ? · requis
    The decoded PAYMENT-REQUIRED header JSON (object), or the raw base64 header value (string).
  • expect · object · optionnel
    What you are about to pay; checked against the signed fields.
  • keys_url · string · optionnel
    Override the seller's public-key URL (defaults to extensions.signedRequirements.keys_url).

  Exemple d'appel

  {"name": "verify_payment_requirements", "arguments": {"body": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://oceanalt.com/api/mcp