Koskamo

OceanAlt AML MCP

OceanAlt provides a pre-payment decision service for AI agents, offering sanctions and AML screening of payees, payment pages, and requests. The MCP server enables agents to check if a payee is risky, if a URL is a phishing host, and if a payment request is genuine before money moves, supporting both free and paid x402 interfaces.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

OceanAlt AML MCP logo, by OceanAltVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by OceanAlt
MCP endpoint (Streamable HTTP)
https://oceanalt.com/api/mcp
Vendor documentation

What its tools do

13 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (12)

Can change data (1)

13 of 13 have a description · 13 of 13 declare behavior hints · 8 of 11 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to oceanalt.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Screen payee addresses for sanctions and AML risks
  • Check payment URLs for phishing or brand imitation
  • Verify payment requests (emails/invoices) for spoofing
  • Decode transaction intent to detect unlimited approvals

Source and maintenance

Vendor evidenceRegistry 0.7.6
mcp-registry: com.oceanalt/aml@0.7.6Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
oceanalt-aml 0.7.6
MCP protocol negotiated in check
2025-11-25
Tools
13 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
1 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

OceanAlt: free pre-payment checks for agents, no signup and no API key. When to call: whenever a task involves paying, sending, transferring or tipping money or crypto, buying something, settling an invoice, or answering an x402 payment quote, before any funds move. Start here: before every payment, call payment_decision with the payee address (to) and network; if the answer is not allow, do not pay. Try it now with {"to":"0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b","network":"ethereum"}, a known mixer, which returns decline with the matching list as evidence. Then, as needed: screen_endpoint on the payment page URL (catches lookalike domains), check_payment_request when an email, invoice or message asks you to pay (spoofed sender, phishing links, changed payee), screen_address for a raw verdict on any address. All of these are free (anonymous use is limited to 2,000 calls a month per IP; a free API key gives 5,000). The prompt check_before_paying runs them in order.

Tools

13 advertised

payment_decision — Call before every payment: allow, review or decline (free, no API key)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Call before sending funds, buying a service, settling an invoice or answering an x402 payment quote. Pass the payee address (to) and network to get allow | review | decline, evidence and retry semantics. Only an explicit allow passes this risk check; review, decline, missing or unknown decisions and errors are not permission to pay. This tool does not transfer funds or grant payment authorization. A signed receipt or attestation records the decision, including review; a valid signature does not turn review into approval or prove settlement. If a receipt is returned, its Ed25519 signature can be verified with the public key at https://oceanalt.com/.well-known/oceanalt-keys.json. Pass resource_url to check the origin's payment quote against the payee; a different payee or an unavailable check raises the decision to review. A match is not an endorsement of the seller. Free within the monthly allowance; no signup or key is required to start. Anonymous allowance exhaustion is an error, not a risk decision.

payment_decision input schema
{
  "type": "object",
  "required": [
    "to"
  ],
  "properties": {
    "to": {
      "type": "string",
      "examples": [
        "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
      ],
      "description": "Payee address the agent is about to pay: 0x (EVM), T… (TRON), Solana, Bitcoin or r… (XRP Ledger); list matching only: Monero (4…/8…), Bitcoin Cash (q…/p…, optional bitcoincash: prefix), Litecoin (ltc1…) or BNB Beacon Chain (bnb1…)."
    },
    "lang": {
      "enum": [
        "en",
        "zh"
      ],
      "type": "string",
      "description": "Language for human-readable fields (signals, note, advice). Defaults to English."
    },
    "task": {
      "type": "string",
      "description": "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": {
      "enum": [
        "ethereum",
        "base",
        "bsc",
        "polygon",
        "arbitrum",
        "optimism",
        "avalanche",
        "arc"
      ],
      "type": "string",
      "description": "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": {
      "type": "string",
      "description": "Short purpose/memo (optional)."
    },
    "reasoning": {
      "type": "string",
      "description": "Optional payment intent: why this payee. Instruction-override phrases here route the payment to review."
    },
    "amountUsdc": {
      "type": "number",
      "description": "Amount in USDC (optional; recorded, not required for the decision)."
    },
    "resource_url": {
      "type": "string",
      "description": "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": {
      "type": "number",
      "description": "Optional declared per-payment cap in USDC. amountUsdc above it → decline."
    }
  }
}
payment_decision output schema
{
  "type": "object",
  "anyOf": [
    {
      "required": [
        "decision",
        "allow",
        "address",
        "verdict",
        "signal_keys",
        "reason_code",
        "retry"
      ]
    },
    {
      "required": [
        "reason_code",
        "code",
        "retry"
      ],
      "properties": {
        "reason_code": {
          "const": "invalid_input"
        }
      }
    }
  ],
  "properties": {
    "code": {
      "type": "string",
      "description": "Input error code, e.g. unknown_network, network_address_mismatch, unparsable_url."
    },
    "lang": {
      "enum": [
        "en",
        "zh"
      ],
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "risk": {
      "type": [
        "number",
        "null"
      ],
      "maximum": 100,
      "minimum": 0,
      "description": "Rounded to 10 when detail_level is coarse."
    },
    "allow": {
      "type": "boolean",
      "description": "if (!allow) do not pay."
    },
    "error": {
      "type": "string",
      "description": "Present only on an input error (isError: true)."
    },
    "retry": {
      "enum": [
        "non_retryable",
        "not_applicable",
        "policy_dependent_backoff",
        "retry_after_authorization",
        "retry_after_fix",
        "retryable_after_funding"
      ],
      "type": "string"
    },
    "cached": {
      "type": "boolean"
    },
    "address": {
      "type": "string"
    },
    "blocked": {
      "type": "boolean"
    },
    "receipt": {
      "type": "object",
      "description": "Ed25519-signed decision receipt: { signed, signature_ed25519, note }. Verify with https://oceanalt.com/.well-known/oceanalt-keys.json."
    },
    "signals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Human-readable. Do not branch on these."
    },
    "verdict": {
      "enum": [
        "clear",
        "caution",
        "risky",
        "uncertain",
        "unknown"
      ],
      "type": "string",
      "description": "clear means no match in the data held, not that it is safe. uncertain must never be treated as clear."
    },
    "decision": {
      "enum": [
        "allow",
        "review",
        "decline"
      ],
      "type": "string"
    },
    "evidence": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "standard": {
      "type": "string",
      "format": "uri"
    },
    "risk_band": {
      "enum": [
        "low",
        "medium",
        "high",
        null
      ],
      "type": [
        "string",
        "null"
      ]
    },
    "retry_hint": {
      "type": "string"
    },
    "settlement": {
      "type": "object",
      "properties": {
        "verify_url": {
          "type": "string",
          "format": "uri"
        },
        "attestation_id": {
          "type": "string"
        }
      }
    },
    "detail_note": {
      "type": "string"
    },
    "reason_code": {
      "type": "string",
      "description": "Stable reason code; table at https://oceanalt.com/api/contract."
    },
    "signal_keys": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Language-independent keys. Branch on these. Full list at https://oceanalt.com/api/contract."
    },
    "detail_level": {
      "enum": [
        "full",
        "coarse"
      ],
      "type": "string"
    },
    "evaluated_at": {
      "type": "string",
      "format": "date-time"
    },
    "intelligence": {
      "type": "object"
    },
    "intent_check": {
      "type": "object"
    },
    "signal_class": {
      "type": "string"
    },
    "evidence_as_of": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      }
    },
    "origin_binding": {
      "type": "object",
      "properties": {
        "payee_origin_binding": {
          "enum": [
            "bound",
            "unbound",
            "not_evaluated",
            "indeterminate"
          ],
          "type": "string"
        }
      }
    },
    "evidence_oldest": {
      "type": [
        "string",
        "null"
      ]
    },
    "screening_scope": {
      "type": "object",
      "properties": {
        "note": {
          "type": "string"
        },
        "chain": {
          "type": "string"
        },
        "coverage": {
          "enum": [
            "list_only"
          ],
          "type": "string"
        },
        "onchain_analysis": {
          "type": "boolean"
        }
      },
      "description": "Present only for list-only chains: coverage is list_only, no on-chain analysis is performed."
    },
    "screened_network": {
      "type": "string"
    },
    "accepted_networks": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "payee_fulfillment": {
      "type": "object"
    },
    "requires_information": {
      "type": "object"
    },
    "evidence_qualification": {
      "type": "object"
    }
  }
}
payment_decision annotations
{
  "title": "Payment decision (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
screen_address — Screen a payee address for AML risk (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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, Bitcoin and XRP Ledger (r…); Monero, Bitcoin Cash, Litecoin (ltc1) and BNB Beacon (bnb1) by list matching only. Free, no API key.

screen_address input schema
{
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "lang": {
      "enum": [
        "en",
        "zh"
      ],
      "type": "string",
      "description": "Language for human-readable fields (signals, note, advice). Defaults to English."
    },
    "address": {
      "type": "string",
      "examples": [
        "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
      ],
      "description": "Address to screen. EVM: 0x + 40 hex. Tron: T + 33 base58. Solana: base58 public key. Bitcoin: bc1… / 1… / 3…. XRP Ledger: r…. List matching only: Monero (4…/8…, 95 chars), Bitcoin Cash (q…/p…, optional bitcoincash: prefix), Litecoin (ltc1…), BNB Beacon Chain (bnb1…)."
    },
    "network": {
      "enum": [
        "ethereum",
        "base",
        "bsc",
        "polygon",
        "arbitrum",
        "optimism",
        "avalanche",
        "arc"
      ],
      "type": "string",
      "description": "EVM chain (optional; auto-defaults to ethereum; ignored for Tron, Solana, Bitcoin and XRP Ledger)."
    }
  }
}
screen_address output schema
{
  "type": "object",
  "anyOf": [
    {
      "required": [
        "verdict",
        "blocked",
        "signal_keys",
        "reason_code",
        "retry"
      ]
    },
    {
      "required": [
        "reason_code",
        "code",
        "retry"
      ],
      "properties": {
        "reason_code": {
          "const": "invalid_input"
        }
      }
    }
  ],
  "properties": {
    "code": {
      "type": "string",
      "description": "Input error code, e.g. unknown_network, network_address_mismatch, unparsable_url."
    },
    "note": {
      "type": "string"
    },
    "risk": {
      "type": [
        "number",
        "null"
      ],
      "maximum": 100,
      "minimum": 0,
      "description": "Rounded to 10 when detail_level is coarse."
    },
    "error": {
      "type": "string",
      "description": "Present only on an input error (isError: true)."
    },
    "retry": {
      "enum": [
        "non_retryable",
        "not_applicable",
        "policy_dependent_backoff",
        "retry_after_authorization",
        "retry_after_fix",
        "retryable_after_funding"
      ],
      "type": "string"
    },
    "cached": {
      "type": "boolean"
    },
    "blocked": {
      "type": "boolean"
    },
    "signals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Human-readable. Do not branch on these."
    },
    "verdict": {
      "enum": [
        "clear",
        "caution",
        "risky",
        "uncertain",
        "unknown"
      ],
      "type": "string",
      "description": "clear means no match in the data held, not that it is safe. uncertain must never be treated as clear."
    },
    "evidence": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "provider": {
      "type": "string"
    },
    "risk_band": {
      "enum": [
        "low",
        "medium",
        "high",
        null
      ],
      "type": [
        "string",
        "null"
      ]
    },
    "retry_hint": {
      "type": "string"
    },
    "detail_note": {
      "type": "string"
    },
    "reason_code": {
      "type": "string",
      "description": "Stable reason code; table at https://oceanalt.com/api/contract."
    },
    "signal_keys": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Language-independent keys. Branch on these. Full list at https://oceanalt.com/api/contract."
    },
    "detail_level": {
      "enum": [
        "full",
        "coarse"
      ],
      "type": "string"
    },
    "evaluated_at": {
      "type": "string",
      "format": "date-time"
    },
    "signal_class": {
      "type": "string"
    },
    "evidence_as_of": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      }
    },
    "evidence_oldest": {
      "type": [
        "string",
        "null"
      ]
    },
    "screening_scope": {
      "type": "object",
      "properties": {
        "note": {
          "type": "string"
        },
        "chain": {
          "type": "string"
        },
        "coverage": {
          "enum": [
            "list_only"
          ],
          "type": "string"
        },
        "onchain_analysis": {
          "type": "boolean"
        }
      },
      "description": "Present only for list-only chains: coverage is list_only, no on-chain analysis is performed."
    },
    "screened_network": {
      "type": "string",
      "description": "The chain actually screened: tron, solana, bitcoin and xrpl follow the address format; an 0x address uses network, or ethereum when none was given. List-only chains (monero, bitcoin-cash, litecoin, bnb-beacon, and dogecoin, dash, zcash etc. for list hits) are named here and described in screening_scope."
    },
    "accepted_networks": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "requires_information": {
      "type": "object"
    },
    "evidence_qualification": {
      "type": "object"
    }
  }
}
screen_address annotations
{
  "title": "Screen address (AML, free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
screen_endpoint — Screen a payment endpoint for phishing (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

screen_endpoint input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Full URL or bare domain of the payment endpoint, e.g. https://pay.example.com/x402 or pay.example.com"
    },
    "lang": {
      "enum": [
        "en",
        "zh"
      ],
      "type": "string",
      "description": "Language for human-readable fields. Defaults to English."
    }
  }
}
screen_endpoint output schema
{
  "type": "object",
  "anyOf": [
    {
      "required": [
        "host",
        "verdict",
        "signal_keys",
        "reason_code",
        "retry"
      ]
    },
    {
      "required": [
        "reason_code",
        "code",
        "retry"
      ],
      "properties": {
        "reason_code": {
          "const": "invalid_input"
        }
      }
    }
  ],
  "properties": {
    "code": {
      "type": "string",
      "description": "Input error code, e.g. unknown_network, network_address_mismatch, unparsable_url."
    },
    "host": {
      "type": "string"
    },
    "note": {
      "type": "string"
    },
    "risk": {
      "type": [
        "number",
        "null"
      ],
      "maximum": 100,
      "minimum": 0,
      "description": "Rounded to 10 when detail_level is coarse."
    },
    "error": {
      "type": "string",
      "description": "Present only on an input error (isError: true)."
    },
    "input": {
      "type": "string"
    },
    "retry": {
      "enum": [
        "non_retryable",
        "not_applicable",
        "policy_dependent_backoff",
        "retry_after_authorization",
        "retry_after_fix",
        "retryable_after_funding"
      ],
      "type": "string"
    },
    "signals": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Human-readable. Do not branch on these."
    },
    "verdict": {
      "enum": [
        "clear",
        "caution",
        "risky",
        "uncertain",
        "unknown"
      ],
      "type": "string",
      "description": "clear means no match in the data held, not that it is safe. uncertain must never be treated as clear."
    },
    "evidence": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "imitates": {
      "type": "object",
      "required": [
        "brand",
        "label",
        "official"
      ],
      "properties": {
        "brand": {
          "type": "string"
        },
        "label": {
          "type": "string"
        },
        "official": {
          "type": "string"
        }
      },
      "description": "Present when the host imitates a known brand."
    },
    "listed_as": {
      "type": "object",
      "description": "Present when the host or a parent domain is on a phishing list: source, label, firstSeen, lastSeen, delistedAt."
    },
    "risk_band": {
      "enum": [
        "low",
        "medium",
        "high",
        null
      ],
      "type": [
        "string",
        "null"
      ]
    },
    "retry_hint": {
      "type": "string"
    },
    "detail_note": {
      "type": "string"
    },
    "reason_code": {
      "type": "string",
      "description": "Stable reason code; table at https://oceanalt.com/api/contract."
    },
    "signal_keys": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Language-independent keys. Branch on these. Full list at https://oceanalt.com/api/contract."
    },
    "detail_level": {
      "enum": [
        "full",
        "coarse"
      ],
      "type": "string"
    },
    "signal_class": {
      "type": "string"
    },
    "accepted_networks": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}
screen_endpoint annotations
{
  "title": "Screen payment endpoint (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
check_payment_request — Check an email, invoice or message that asks you to pay (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

check_payment_request input schema
{
  "type": "object",
  "properties": {
    "body": {
      "type": "string",
      "description": "Plain-text body, invoice text or chat message"
    },
    "from": {
      "type": "string",
      "description": "The From line, e.g. \"Acme Billing\" <billing@acme.com>"
    },
    "lang": {
      "enum": [
        "en",
        "zh"
      ],
      "type": "string",
      "description": "Language for human-readable fields. Defaults to English."
    },
    "pay_to": {
      "type": "string",
      "description": "The payee address the message asks you to pay, if you already extracted it"
    },
    "headers": {
      "type": "string",
      "description": "Raw email headers, if available (needed to check SPF/DKIM/DMARC)"
    },
    "network": {
      "type": "string",
      "description": "Network of pay_to, e.g. base, ethereum, tron, solana"
    },
    "subject": {
      "type": "string"
    },
    "reply_to": {
      "type": "string",
      "description": "The Reply-To line, if any"
    },
    "body_html": {
      "type": "string",
      "description": "HTML body, if available (lets OceanAlt compare link text with where links really go)"
    },
    "previous_pay_to": {
      "type": "string",
      "description": "The address you paid this requester last time, if any"
    },
    "expected_sender_domain": {
      "type": "string",
      "description": "The domain this requester normally sends from, if you know it"
    }
  }
}
check_payment_request output schema
{
  "type": "object",
  "anyOf": [
    {
      "required": [
        "decision",
        "reason_code",
        "signal_keys",
        "findings"
      ]
    },
    {
      "required": [
        "reason_code",
        "code",
        "retry"
      ],
      "properties": {
        "reason_code": {
          "const": "invalid_input"
        }
      }
    }
  ],
  "properties": {
    "decision": {
      "enum": [
        "allow",
        "review",
        "decline"
      ],
      "type": "string"
    },
    "findings": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "reason_code": {
      "type": "string"
    },
    "signal_keys": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}
check_payment_request annotations
{
  "title": "Check a payment request (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
counterparty_control_baseline — Check a counterparty's control baseline before paying (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

counterparty_control_baseline input schema
{
  "type": "object",
  "properties": {
    "entity": {
      "type": "string",
      "description": "The counterparty's entity name."
    },
    "agentId": {
      "type": "string",
      "description": "Their agent id, if you have that instead."
    }
  }
}
counterparty_control_baseline annotations
{
  "title": "Counterparty control baseline (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
attest_control_baseline — File your own control-baseline attestation (free)
Advertised by the server during the last successful anonymous check.
Open-world

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.

attest_control_baseline input schema
{
  "type": "object",
  "required": [
    "entity",
    "answers"
  ],
  "properties": {
    "entity": {
      "type": "string",
      "description": "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": {
      "type": "string",
      "description": "Optional. If this party already has an agent registered with OceanAlt, link the attestation to it."
    },
    "answers": {
      "type": "object",
      "description": "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": {
      "type": "string",
      "description": "Optional contact for follow-up. Not published."
    },
    "gapPlan": {
      "type": "string",
      "description": "For controls answered false: how and when you plan to close them. Plain text."
    }
  }
}
attest_control_baseline annotations
{
  "title": "File a control-baseline attestation (free)",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
baseline_controls — List the control-baseline questions (free)
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

baseline_controls input schema
{
  "type": "object",
  "required": [],
  "properties": {}
}
baseline_controls annotations
{
  "title": "Get the control baseline list (free)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
resolve_agent_identity — Resolve an agent's chain of accountability (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

resolve_agent_identity input schema
{
  "type": "object",
  "required": [
    "agentId"
  ],
  "properties": {
    "agentId": {
      "type": "string",
      "description": "The agent id to resolve."
    }
  }
}
resolve_agent_identity annotations
{
  "title": "Resolve agent identity (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
recent_flagged — List recently flagged addresses (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

recent_flagged input schema
{
  "type": "object",
  "properties": {}
}
recent_flagged annotations
{
  "title": "Recent flagged addresses (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}
verify_payment_requirements — Verify a signed x402 402 response (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

verify_payment_requirements input schema
{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "description": "The decoded PAYMENT-REQUIRED header JSON (object), or the raw base64 header value (string)."
    },
    "expect": {
      "type": "object",
      "properties": {
        "payTo": {
          "type": "string"
        },
        "amount": {
          "type": "string"
        }
      },
      "description": "What you are about to pay; checked against the signed fields."
    },
    "keys_url": {
      "type": "string",
      "description": "Override the seller's public-key URL (defaults to extensions.signedRequirements.keys_url)."
    }
  }
}
verify_payment_requirements annotations
{
  "title": "Verify signed payment requirements (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
check_calldata_intent — Decode calldata and compare with declared intent (free)
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

check_calldata_intent input schema
{
  "type": "object",
  "properties": {
    "data": {
      "type": "string",
      "description": "EVM only: 0x-prefixed hex calldata."
    },
    "value": {
      "type": "string",
      "description": "EVM only: native value in wei (optional)."
    },
    "intent": {
      "type": "object",
      "required": [
        "action",
        "to"
      ],
      "properties": {
        "to": {
          "type": "string",
          "description": "EVM: recipient address. Solana: wallet or token account."
        },
        "asset": {
          "type": "string",
          "description": "EVM: symbol/contract (optional). Solana: mint address (optional, checked against TransferChecked)."
        },
        "action": {
          "enum": [
            "pay"
          ],
          "type": "string"
        },
        "amount": {
          "type": "string",
          "description": "Base units (e.g. 10 USDC = 10000000)."
        }
      }
    },
    "network": {
      "type": "string",
      "description": "'solana' to decode a Solana transaction; EVM chain name or CAIP-2 id otherwise (optional)."
    },
    "contract": {
      "type": "string",
      "description": "EVM only: the transaction's `to` field (token contract for ERC-20 payments, or the recipient for native transfers)."
    },
    "transaction": {
      "type": "string",
      "description": "Solana only: base64-serialized transaction or message."
    }
  }
}
check_calldata_intent annotations
{
  "title": "Check calldata against intent (free)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
payee_decide — Payee-side decision: accept this payment? (free)
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

payee_decide input schema
{
  "type": "object",
  "required": [
    "payee"
  ],
  "properties": {
    "payee": {
      "type": "string",
      "description": "The payee's registry id (sid)."
    },
    "payer": {
      "type": "object",
      "properties": {
        "address": {
          "type": "string"
        },
        "agentId": {
          "type": "string"
        }
      },
      "description": "Who is paying (optional)."
    },
    "network": {
      "type": "string",
      "description": "Chain of the payment (optional)."
    },
    "purpose": {
      "type": "string",
      "description": "What the payment is for (optional)."
    },
    "amountUsdc": {
      "type": "number",
      "description": "Amount in USDC (optional)."
    }
  }
}
payee_decide annotations
{
  "title": "Payee-side decision (free)",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
evidence_bundle — Signed evidence bundle for an address (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

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.

evidence_bundle input schema
{
  "type": "object",
  "required": [
    "address"
  ],
  "properties": {
    "address": {
      "type": "string"
    },
    "network": {
      "type": "string",
      "description": "EVM chain name (optional, default ethereum)."
    }
  }
}
evidence_bundle annotations
{
  "title": "Evidence bundle (free)",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

1 advertised

check_before_paying — Check before paying

Advertised by the server during the last successful anonymous check.

Run OceanAlt's pre-payment checks in the right order before any money moves: payee, payment page, and the message that asked for payment.

payee
Address you are about to pay: 0x (EVM), T… (TRON), Solana, Bitcoin or r… (XRP Ledger); list matching only: Monero (4…/8…), Bitcoin Cash (q…/p…, optional bitcoincash: prefix), Litecoin (ltc1…) or BNB Beacon Chain (bnb1…). (required)
network
EVM chain for a 0x address, e.g. base or ethereum. Leave empty for other chains.
page_url
URL of the payment page or of the API that returned the 402 quote, if any.
request_text
The email, invoice or chat message that asked for this payment, if any.

Resources

0 advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1968 ms
95th percentile latency
1968 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1968 ms · metadata changed · 13 tool(s), 0 resource(s), 0 resource template(s), 1 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http oceanalt-aml-mcp https://oceanalt.com/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add oceanalt-aml-mcp --url https://oceanalt.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable oceanalt-aml-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "oceanalt-aml-mcp": {
      "url": "https://oceanalt.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "oceanalt-aml-mcp": {
      "type": "streamableHttp",
      "url": "https://oceanalt.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start oceanalt-aml-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "oceanalt-aml-mcp": {
      "type": "http",
      "url": "https://oceanalt.com/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http oceanalt-aml-mcp https://oceanalt.com/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://oceanalt.com/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "oceanalt-aml-mcp": {
      "serverUrl": "https://oceanalt.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like OceanAlt AML MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 671

Do you run OceanAlt AML MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing