Skip to content

LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server

com.usdtbanned/mayakusdtbanned.comstreamable-httpv1.0.0Scanned

USDT freeze risk for any address: Tether blacklist status and open multisig freeze proposals.

15 tools: 1 can delete or cancel things, 1 do something that can't be undone, 4 change things and 9 only read.

Tools: 1 delete, 1 irreversible, 4 write, 9 read.
  • Reads private data · 1
  • Reads text others write · 6
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does 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.
Govern this server →

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 LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server can do

The LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server is published by usdtbanned.com, a domain the MCP Registry verified. It has 15 tools. It can delete or cancel things (1 tool: watchlist_remove), do things that cannot be undone, such as sending, paying or publishing (submit_payment) and create or change data (4 tools: check_address, check_addresses, watchlist_add and create_order). 9 tools only read.

1 tool reads private data (fetch); 6 tools bring in text other people can write (check_address, fetch, list_open_proposals and 3 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 15, 2026, version 1.0.0.

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.

15 tools

Deletes or cancels 1Claude Code: deny
  • watchlist_removeRemove an address from the user's LIGHTHOUSE monitoring list.No findings

    Why it is in this group

    • The name "watchlist_remove" says "remove": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove an address from the user's LIGHTHOUSE monitoring list. Requires sign-in.

    Annotations the server declares

    • title: Remove address from monitoring
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • submit_paymentAfter sending USDT TRC-20 for an order, pass the order_id and the Tron transaction hash.Reads text others writeNo findings

    Why it is in this group

    • The name "submit_payment" says "submit": a word for a change.
    • The name "submit_payment" also says "payment": a word that usually means money moves, which cannot be taken back.

    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
    After sending USDT TRC-20 for an order, pass the order_id and the Tron transaction hash. The service finds the transfer on-chain, checks recipient and exact amount and, once confirmed (~1 minute), issues or extends the API key. Returns a verdict: paid, unconfirmed, wrong_amount, wrong_recipient or not_found.

    Annotations the server declares

    • title: Submit a USDT payment for an order
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Changes things 4Claude Code: ask
  • check_addressCheck whether a crypto address is at risk of a USDT (Tether) freeze or is already frozen.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
    Check whether a crypto address is at risk of a USDT (Tether) freeze or is already frozen. Covers Ethereum, Tron, Avalanche, Celo, Solana and TON. Returns risk level 0–3 (0 no risk, 1 freeze proposal open in Tether multisig, 2 second of three signatures collected, 3 blacklisted), recommended action, per-chain reasons, current USDT balance, open freeze proposals with execution probability, and past blacklist episodes. Use it before accepting, sending or holding USDT, for counterparty due diligence, or when a user asks whether a wallet is blacklisted/frozen by Tether.

    Annotations the server declares

    • title: Check USDT freeze risk
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • check_addressesCheck up to 20 addresses at once for USDT freeze risk (database check without live node calls).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
    Check up to 20 addresses at once for USDT freeze risk (database check without live node calls). Returns level 0–3, label and action for each address, sorted by risk. Use for screening payout lists, deposit addresses or CSV exports.

    Annotations the server declares

    • title: Batch check USDT freeze risk
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • create_orderCreate an order for a LIGHTHOUSE plan paid in crypto.Reads text others writeNo findings

    Why it is in this group

    • The name "create_order" says "create": a word for a change.

    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
    Create an order for a LIGHTHOUSE plan paid in crypto. payment_method=usdt_trc20 (default): returns the Tron address and the exact USDT amount (unique cents identify the order), valid 60 minutes; after sending, call submit_payment with the tx hash, then get_order returns the API key. payment_method=x402: returns x402 v2 PaymentRequired (USDC on Base); retry the same call with the signed payload in _meta["x402/payment"] and the API key is returned immediately. Without sign-in the key is not linked to an account; extend=true requires sign-in; monitoring needs the key to be linked to an account. Never send funds without the user's explicit approval.

    Annotations the server declares

    • title: Buy a LIGHTHOUSE plan with crypto
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • watchlist_addPut an address on LIGHTHOUSE monitoring (up to 10 per account).No findings

    Why it is in this group

    • The name "watchlist_add" says "add": a word for a change.
    Description, as the server wrote it
    Put an address on LIGHTHOUSE monitoring (up to 10 per account). Risk is re-checked every 10 minutes and right after Tether multisig events; the user gets a Telegram or e-mail notification when the level changes. Requires sign-in and an active monitoring subscription or LIGHTHOUSE plan.

    Annotations the server declares

    • title: Add address to monitoring
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 9Show 9 read-only tools
  • fetchFetch the full text of a search result by id (address:<address>, doc:<name> or stats:overview).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "doc": it reads documents.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch the full text of a search result by id (address:<address>, doc:<name> or stats:overview).

    Annotations the server declares

    • title: Fetch LIGHTHOUSE record
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_accountShow the signed-in user's LIGHTHOUSE plan, expiry dates, monitoring subscription and how many addresses are monitored.No findings

    Why it is in this group

    • The name "get_account" says "get": a word for reading.
    Description, as the server wrote it
    Show the signed-in user's LIGHTHOUSE plan, expiry dates, monitoring subscription and how many addresses are monitored. Requires sign-in.

    Annotations the server declares

    • title: My LIGHTHOUSE account
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_freeze_statisticsCurrent statistics of the USDT blacklist across all chains: number of blacklisted addresses, frozen USDT, freezes in the last 24 h / 30 days, open freeze proposals, median delay fr…No findings

    Why it is in this group

    • The name "get_freeze_statistics" says "get": a word for reading.
    Description, as the server wrote it
    Current statistics of the USDT blacklist across all chains: number of blacklisted addresses, frozen USDT, freezes in the last 24 h / 30 days, open freeze proposals, median delay from proposal to freeze by chain, delay distribution and monthly dynamics for the last 12 months.

    Annotations the server declares

    • title: USDT blacklist statistics
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_orderGet the status of a LIGHTHOUSE order (pending, paid, expired).Reads text others writeNo findings

    Why it is in this group

    • The name "get_order" says "get": 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
    Get the status of a LIGHTHOUSE order (pending, paid, expired). When paid, returns the API key (for api plans) or the monitoring expiry (for watch plans). Checks incoming transfers on each call.

    Annotations the server declares

    • title: Order status and API key
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_plansList LIGHTHOUSE paid plans (API key with dashboard, webhooks and monitoring; or address monitoring only), prices in USDT and accepted crypto payment methods: USDT TRC-20 on Tron (a…No findings

    Why it is in this group

    • The name "get_plans" says "get": a word for reading.
    Description, as the server wrote it
    List LIGHTHOUSE paid plans (API key with dashboard, webhooks and monitoring; or address monitoring only), prices in USDT and accepted crypto payment methods: USDT TRC-20 on Tron (always) and x402 USDC on Base (if enabled). Address checks are free; buy a plan when you need the REST API at scale, open freeze proposals or monitoring.

    Annotations the server declares

    • title: LIGHTHOUSE plans and payment methods
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_open_proposalsList freeze (addBlackList) and unfreeze proposals that are open in Tether multisigs but not yet executed — the early-warning signal before an address is frozen.Reads text others writeNo findings

    Why it is in this group

    • The name "list_open_proposals" says "list": 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
    List freeze (addBlackList) and unfreeze proposals that are open in Tether multisigs but not yet executed — the early-warning signal before an address is frozen. Each item has address, chain, signatures collected/required, age, probability of execution within 10 min and 1 h, and USDT amount at risk. Requires sign-in.

    Annotations the server declares

    • title: Open Tether freeze proposals
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_recent_freezesLog of executed blacklist operations, newest first: freezes (add), unfreezes (rem) or fund destructions (des), with address, chain, time, delay from proposal and amount.No findings

    Why it is in this group

    • The name "list_recent_freezes" says "list": a word for reading.
    Description, as the server wrote it
    Log of executed blacklist operations, newest first: freezes (add), unfreezes (rem) or fund destructions (des), with address, chain, time, delay from proposal and amount. Requires sign-in.

    Annotations the server declares

    • title: Recent USDT freezes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • watchlist_listList the user's addresses on LIGHTHOUSE monitoring with their current risk level, last check time and last level change.No findings

    Why it is in this group

    • The name "watchlist_list" says "list": a word for reading.
    Description, as the server wrote it
    List the user's addresses on LIGHTHOUSE monitoring with their current risk level, last check time and last level change. Requires sign-in.

    Annotations the server declares

    • title: My monitored addresses
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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 outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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.

Tools listed without sign-in

Looked at Nov 16, 2026, 14:19 UTC, unchanged since Nov 16, 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
6
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://usdtbanned.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://usdtbanned.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://usdtbanned.com/mcp: tools/list returned 15 tools to an anonymous client, including watchlist_remove (destructive), submit_payment (irreversible), check_address (write), check_addresses (write), watchlist_add (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http mayak https://usdtbanned.com/mcp
claude mcp add --transport http mayak https://usdtbanned.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__mayak__get_freeze_statistics",
      "mcp__mayak__search",
      "mcp__mayak__fetch",
      "mcp__mayak__list_open_proposals",
      "mcp__mayak__list_recent_freezes",
      "mcp__mayak__get_account",
      "mcp__mayak__watchlist_list",
      "mcp__mayak__get_plans",
      "mcp__mayak__get_order"
    ],
    "ask": [
      "mcp__mayak__check_address",
      "mcp__mayak__check_addresses",
      "mcp__mayak__watchlist_add",
      "mcp__mayak__create_order",
      "mcp__mayak__submit_payment"
    ],
    "deny": [
      "mcp__mayak__watchlist_remove"
    ]
  }
}

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 mayak. Review it before you use it.

Capability tags behind 6 rules
  • mcp__mayak__check_address untrusted-input
  • mcp__mayak__fetch private-data, untrusted-input
  • mcp__mayak__list_open_proposals untrusted-input
  • mcp__mayak__create_order untrusted-input
  • mcp__mayak__submit_payment untrusted-input
  • mcp__mayak__get_order 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.usdtbanned/mayak/verify?hash=39cd45e6768659ad58ac7064ca6ba3ac39a8cb6c354f1fc2b6d4b557053bd13d" | jq -e '.changed == false'

Pinned hash 39cd45e67686, from Nov 15, 2026, 14:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.usdtbanned/mayak/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.usdtbanned/mayak
[![Anlyon Radar](https://radar.anlyon.com/badge/com.usdtbanned/mayak.svg)](https://radar.anlyon.com/servers/com.usdtbanned/mayak)

Source: MCP Registry. Synced Nov 15, 2026, 14:17 UTC.

LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 6 of which can change, send or delete something, and 0 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 LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: watchlist_remove.

Can the LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: submit_payment.

What tools does the LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server have?

15 tools: 1 destructive, 1 irreversible, 4 write, 9 read. watchlist_remove, submit_payment, check_address, check_addresses, watchlist_add, create_order, get_freeze_statistics, search and 7 more.

Does the LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the LIGHTHOUSE (МАЯК) — USDT freeze risk MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.