aml MCP server
com.oceanalt/amloceanalt.comstreamable-httpv0.7.7Scanned
Pre-payment checks for AI agents: sanctions and AML screening of payees, payment pages and requests.
13 tools: 4 do something that can't be undone, 6 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 10
- Can send data out · 3
- 9 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the aml MCP server can do
The aml MCP server is published by oceanalt.com, a domain the MCP Registry verified. It has 13 tools. It can do things that cannot be undone, such as sending, paying or publishing (payment_decision, check_payment_request, verify_payment_requirements and check_calldata_intent) and create or change data (6 tools: screen_address, screen_endpoint, counterparty_control_baseline, attest_control_baseline and 2 more), but cannot delete data. 3 tools only read.
10 tools bring in text other people can write (payment_decision, screen_address, screen_endpoint and 7 more); 3 tools can send data out of your system (payment_decision, screen_endpoint and check_calldata_intent).
The fixed checks matched 9 findings (base64-blob, annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 0.7.7.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Can't be undone 4Claude Code: ask
check_calldata_intentAnti blind-signing.Can send data out1 finding
Why it is in this group
- The input addresses people (input.intent.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.intent.to): what the tool writes goes there.
Findings
- Warn
The server marks "check_calldata_intent" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.intent.to): what it sends cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- title: Check calldata against intent (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_payment_requestCall this before paying because an email, invoice or chat message asked you to.Reads text others write1 finding
Why it is in this group
- The name "check_payment_request" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "check_payment_request" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_payment_request" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- title: Check a payment request (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
payment_decisionCall before sending funds, buying a service, settling an invoice or answering an x402 payment quote.Reads text others writeCan send data out2 findings
Why it is in this group
- The name "payment_decision" says "payment": a word that usually means money moves, which cannot be taken back.
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The input schema at properties.to.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.to.examples[0]: "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
- Warn
The server marks "payment_decision" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "payment_decision" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- title: Payment decision (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_payment_requirementsBefore 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, C…Reads text others write1 finding
Why it is in this group
- The name "verify_payment_requirements" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "verify_payment_requirements" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "verify_payment_requirements" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- title: Verify signed payment requirements (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 6Claude Code: ask
attest_control_baselineFile your operator's control-baseline attestation: it publishes what controls YOUR side runs, so payers can see it before settling with you.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it File your operator's control-baseline attestation: it publishes what controls 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 still shows a payer which controls are in place. Control ids are those in the OceanAlt Agent Control Baseline. Only file for a party you are actually authorised to speak for.
Annotations the server declares
- title: File a control-baseline attestation (free)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
counterparty_control_baselineAnswers a different question from address screening.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Counterparty control baseline (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
evidence_bundleUse when you need a record you can keep or hand to someone else, for example when a reviewer, auditor or counterparty asks why a payment to this address was allowed or refused.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
Description, as the server wrote it Use when you need a record you can keep or hand to someone else, for example when a reviewer, auditor or counterparty asks why a payment to this address was allowed or refused. Returns 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. The response includes the signature and the key URL (https://oceanalt.com/.well-known/oceanalt-keys.json) to verify it. A witness, not a prosecutor: no conclusions about people. It does not return a pay / do-not-pay decision. Same as GET https://oceanalt.com/api/evidence/bundle. Free, no API key.
Annotations the server declares
- title: Evidence bundle (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
payee_decideThe receiving side's check before settlement.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Payee-side decision (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
screen_addressRun an AML compliance screen on a single blockchain address BEFORE paying or receiving from it — the pre-payment check on a counterparty.Reads text others write2 findings
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
- Warn
The server marks "screen_address" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Screen address (AML, free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
screen_endpointScreen a payment ENDPOINT (URL or domain) before calling it — the half that address screening cannot answer.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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. It does not check the payee address. Free, no API key.
Annotations the server declares
- title: Screen payment endpoint (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 3Show 3 read-only tools
baseline_controlsFetch 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.No findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
Description, as the server wrote it 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. An attestation uses the control ids it returns. Each control carries which gate enforces it and why it exists.
Annotations the server declares
- title: Get the control baseline list (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recent_flaggedReturn 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.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Recent flagged addresses (free)
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
resolve_agent_identityUse when another AI agent asks you to pay it, or wants to pay you, and you have its agent id: this tells you who is accountable for that agent.Reads text others write1 finding
Why it is in this group
- The name "resolve_agent_identity" says "resolve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...chain agent -> principal -> mandate -> credential -> wallet. Each link reports whether it..."
Description, as the server wrote it Use when another AI agent asks you to pay it, or wants to pay you, and you have its agent id: this tells you who is accountable for that agent. Resolves the chain 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 spending ceiling exists, never its value), so found:false means the agent has not published — absence of information, not a bad signal. This checks the agent, not the payee address. Free, no API key.
Annotations the server declares
- title: Resolve agent identity (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:43 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (4 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://oceanalt.com/api/mcp: tools/list returned 13 tools to an anonymous client, including payment_decision (irreversible), check_payment_request (irreversible), verify_payment_requirements (irreversible), check_calldata_intent (irreversible), screen_address (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
- Warnpayment_decision
The input schema at properties.to.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.to.examples[0]: "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
- Warnpayment_decision
The server marks "payment_decision" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "payment_decision" says "payment": a word that usually means money moves, which cannot be taken back.
- Warnscreen_address
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
- Warnscreen_address
The server marks "screen_address" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
The server marks "check_payment_request" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_payment_request" says "payment": a word that usually means money moves, which cannot be taken back.
The server marks "verify_payment_requirements" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "verify_payment_requirements" says "payment": a word that usually means money moves, which cannot be taken back.
Show 3 more findingsShow fewer
The server marks "check_calldata_intent" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.intent.to): what it sends cannot be taken back.
- Warnevidence_bundle
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0xd90e2f925DA726b50C4Ed8D0Fb90Ad053324F31b"
The description mentions "credential".
What this check looks forMatched text
description: "...chain agent -> principal -> mandate -> credential -> wallet. Each link reports whether it..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools6 changed.~6 changedView diff
- Changed:attest_control_baselineChanges thingsdescriptioninputSchema
- Changed:baseline_controlsOnly readsdescription
- Changed:evidence_bundleChanges thingsdescriptioninputSchema
- Changed:resolve_agent_identityOnly readsdescription
- Changed:screen_endpointChanges thingsdescription
- Changed:verify_payment_requirementsCan't be undoneinputSchema
Tools3 changed.~3 changedView diff
- Changed:evidence_bundleChanges thingsdescriptioninputSchema
- Changed:payment_decisionCan't be undonedescription
- Changed:resolve_agent_identityOnly readsdescriptioninputSchema
Tools2 changed.~2 changedView diff
- Changed:payment_decisionCan't be undoneinputSchema
- Changed:screen_addressChanges thingsdescriptioninputSchema
Install
Pinned to version 0.7.7. Values in angle brackets are yours to fill in.
claude mcp add --transport http aml https://oceanalt.com/api/mcpclaude mcp add --transport http aml https://oceanalt.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__aml__baseline_controls",
"mcp__aml__resolve_agent_identity",
"mcp__aml__recent_flagged"
],
"ask": [
"mcp__aml__payment_decision",
"mcp__aml__screen_address",
"mcp__aml__screen_endpoint",
"mcp__aml__check_payment_request",
"mcp__aml__counterparty_control_baseline",
"mcp__aml__attest_control_baseline",
"mcp__aml__verify_payment_requirements",
"mcp__aml__check_calldata_intent",
"mcp__aml__payee_decide",
"mcp__aml__evidence_bundle"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as aml. Review it before you use it.
Capability tags behind 11 rules
- mcp__aml__payment_decision untrusted-input, outbound
- mcp__aml__screen_address untrusted-input
- mcp__aml__screen_endpoint untrusted-input, outbound
- mcp__aml__check_payment_request untrusted-input
- mcp__aml__counterparty_control_baseline untrusted-input
- mcp__aml__attest_control_baseline untrusted-input
- mcp__aml__resolve_agent_identity untrusted-input
- mcp__aml__recent_flagged untrusted-input
- mcp__aml__verify_payment_requirements untrusted-input
- mcp__aml__check_calldata_intent outbound
- mcp__aml__evidence_bundle untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.oceanalt/aml/verify?hash=83f6749573ff6f89a10ad1a5b8ed9c01ba44550c6502b608715ec095472ad92c" | jq -e '.changed == false'Pinned hash 83f6749573ff, from Nov 12, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.oceanalt/aml/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.oceanalt/aml)Source: MCP Registry · repository. Synced Nov 12, 2026, 07:17 UTC.
aml MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the aml MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 10 of which can change, send or delete something, and 9 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the aml MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the aml MCP server do things that cannot be undone?
- Yes. 4 tools can send, pay, publish or merge: payment_decision, check_payment_request, verify_payment_requirements and check_calldata_intent.
What tools does the aml MCP server have?
- 13 tools: 4 irreversible, 6 write, 3 read. payment_decision, check_payment_request, verify_payment_requirements, check_calldata_intent, screen_address, screen_endpoint, counterparty_control_baseline, attest_control_baseline and 5 more.
Does the aml MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the aml MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): payment_decision, screen_endpoint and check_calldata_intent.
Has the aml MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.