Skip to content

Safe-Send Check: crypto support triage, sanctions and scam screening MCP server

dev.workers.agent-arena-base.safe-send-check/safe-send-checksafe-send-check.agent-arena-base.workers.devstreamable-httpv1.8.0Scanned

Crypto support-ticket triage, OFAC wallet screening, chat scam checks. x402 or prepaid USDC key.

11 tools: 3 do something that can't be undone, 7 change things and 1 only read.

Tools: 0 delete, 3 irreversible, 7 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 10
  • Can send data out · 2
  • 3 findings

With Anlyon

3 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.
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 Safe-Send Check: crypto support triage, sanctions and scam screening MCP server can do

The Safe-Send Check: crypto support triage, sanctions and scam screening MCP server is published by safe-send-check.agent-arena-base.workers.dev, a domain the MCP Registry verified. It has 11 tools. It can do things that cannot be undone, such as sending, paying or publishing (screen_payout_recipient_list, check_crypto_address_before_sending and payment_options) and create or change data (7 tools: screen_wallet_ofac_sanctions, check_crypto_chat_message_for_scams, sweep_crypto_chat_messages_for_scams, triage_crypto_support_ticket and 3 more), but cannot delete data. 1 tool only reads.

10 tools bring in text other people can write (screen_wallet_ofac_sanctions, screen_payout_recipient_list, check_crypto_chat_message_for_scams and 7 more); 2 tools can send data out of your system (screen_payout_recipient_list and check_crypto_address_before_sending).

The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.

Its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 1.8.0.

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.

11 tools

Can't be undone 3Claude Code: ask
  • check_crypto_address_before_sendingBefore sending crypto: detects the chain family (EVM, TRON, Bitcoin, Litecoin, Dogecoin, Solana, TON, XRP), verifies checksums, catches token-contract / burn addresses as recipient…Reads text others writeCan send data out1 finding

    Why it is in this group

    • The input addresses people (input.recipient): 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.recipient): what the tool writes goes there.

    Findings

    • Warn

      The server marks "check_crypto_address_before_sending" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.recipient): what it sends cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Before sending crypto: detects the chain family (EVM, TRON, Bitcoin, Litecoin, Dogecoin, Solana, TON, XRP), verifies checksums, catches token-contract / burn addresses as recipients, invisible or look-alike characters, pasted tx hashes or private keys, testnet addresses and address / network mismatches (e.g. a 0x address on TRC-20); flags a missing memo / tag for exchange deposits. Verdict ok / caution / incomplete / do_not_send. PAID: $0.001 per call or 1 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/address-check.

    Annotations the server declares

    • title: Pre-transfer address check (format, checksum, network, memo)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • payment_optionsFREE.1 finding

    Why it is in this group

    • The name "payment_options" 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.

    Findings

    • Warn

      The server marks "payment_options" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "payment_options" says "payment": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    FREE. Prices, the receiving address, the x402-over-MCP retry format, and how to use a prepaid credits key instead (bought with a plain USDC transfer, no x402 client needed).

    Annotations the server declares

    • title: How to pay (free)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • screen_payout_recipient_listBefore payroll, bounty / grant / contributor payouts, airdrops or refunds: up to 200 recipients (optionally with amounts) in ONE call.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "screen_payout_recipient_list" says "payout": a word that usually means money moves, which cannot be taken back.
    • The input addresses people (input.recipients): 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.recipients): what the tool writes goes there.

    Findings

    • Warn

      The server marks "screen_payout_recipient_list" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "screen_payout_recipient_list" says "payout": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Before payroll, bounty / grant / contributor payouts, airdrops or refunds: up to 200 recipients (optionally with amounts) in ONE call. Per row: format, checksum, network, token-contract / burn addresses, pasted tx hashes or keys, OFAC SDN exact match. Whole list: duplicates (paid twice), look-alike pairs (address poisoning or typos), look-alikes of addresses you trust. Returns the rows to pay, the rows to hold and totals. PAID: $0.050 per call or 50 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/payout-check.

    Annotations the server declares

    • title: Payout pre-flight: screen a whole recipient list before a batch payment
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Changes things 7Claude Code: ask
  • check_crypto_chat_message_for_scamsFor community moderation bots and support desks: every link (known crypto-phishing domain list, brand look-alikes of ~90 wallets / exchanges / DeFi apps, homoglyph / punycode, typo…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
    For community moderation bots and support desks: every link (known crypto-phishing domain list, brand look-alikes of ~90 wallets / exchanges / DeFi apps, homoglyph / punycode, typo-squats, free-hosting drainer pages, shorteners), scam scripts in English and Chinese (seed-phrase requests, fake support DMs, wallet "validation", fund recovery, giveaways, airdrop bait), and secrets the sender leaked (returned redacted). Returns allow / review / block, an action and a ready-to-post moderator reply in Chinese and English. PAID: $0.003 per call or 3 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/scam-message-check.

    Annotations the server declares

    • title: Scam check for one crypto chat message (Telegram / Discord moderation, support inbox)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • credits_balanceFREE.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
    FREE. Credits left and calls made on the key sent as the MCP header "Authorization: Bearer ssk_..." (or _meta["safe-send/credits-key"]).

    Annotations the server declares

    • title: Credits left on your key (free)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • credits_claimFREE.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
    FREE. After the transfer from credits_quote has landed on Base, returns your ssk_ credits key (claiming again returns the same key). Then set the MCP header "Authorization: Bearer <key>" or pass _meta["safe-send/credits-key"].

    Annotations the server declares

    • title: Claim the credits key after your transfer (free)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • credits_quoteFREE, no x402 needed.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
    FREE, no x402 needed. Returns a quote id and the EXACT USDC amount to send on Base from your address to this service. After sending, call credits_claim with the quote id to receive an ssk_ key. 1 credit = $0.001 of list price (OFAC check 5, chat message 3, chat sweep of 25 messages 50, address check 1, payout list 50).

    Annotations the server declares

    • title: Buy credits with a plain USDC transfer: get a quote (free)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • screen_wallet_ofac_sanctionsIs this wallet sanctioned?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
    Is this wallet sanctioned? Screens 1-20 addresses (EVM 0x on any chain, Bitcoin, TRON, Solana, Litecoin, XRP, Monero, Zcash, ...) against every digital-currency address on the US Treasury OFAC SDN list (18 asset lists, refreshed from the official data). Use before your agent sends, pays, accepts or onboards crypto. Exact match -> verdict match (do not transact). English + Chinese advice. Not legal advice. PAID: $0.005 per call or 5 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/ofac-sanctions-check.

    Annotations the server declares

    • title: OFAC sanctions screening for crypto wallet addresses
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • sweep_crypto_chat_messages_for_scamsFor moderation bots and support desks clearing a backlog (back-scan a Telegram / Discord group when your bot joins, sweep a moderation queue): up to 25 messages, each with the full…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
    For moderation bots and support desks clearing a backlog (back-scan a Telegram / Discord group when your bot joins, sweep a moderation queue): up to 25 messages, each with the full single-message analysis (phishing domains, brand look-alikes, scam scripts in English and Chinese, leaked keys redacted). Plus: campaigns (the same bad host, fake brand or scam script across messages and senders), per-sender recommendation (ban_candidate / mute_and_review / watch), the ids to remove / hold / warn, and ONE pinned group warning in Chinese and English. $0.002 a message instead of $0.003. PAID: $0.050 per call or 50 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/scam-message-batch.

    Annotations the server declares

    • title: Moderation sweep: scam-check up to 25 chat messages from one group at once
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • triage_crypto_support_ticketFor the helpdesk bots and agents of crypto exchanges, wallets and projects: one customer ticket in Chinese or English -> which of 21 common situations it is (deposit not credited, …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
    For the helpdesk bots and agents of crypto exchanges, wallets and projects: one customer ticket in Chinese or English -> which of 21 common situations it is (deposit not credited, wrong network, missing memo / tag, stuck tx, bridge delay, tokens not showing, fake support DMs, address poisoning, leaked seed phrase, approval drain, phishing site, "fund recovery" scam, hacked account, no gas, ...), priority P0-P3, an honest recoverability call, the networks / coins / amounts / TxIDs / addresses found and what to ask for next, a ready reply in Chinese AND English, the internal note, a pre-filled escalation ticket and the red lines. A seed phrase or private key the customer pasted is caught and redacted (P0). Rule-based, no model. $0.04 a ticket. PAID: $0.040 per call or 40 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/support-ticket-triage.

    Annotations the server declares

    • title: Crypto support ticket triage for exchange / wallet helpdesks (situation, priority, bilingual reply)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • detect_address_poisoning_lookalikeCompare a destination address with up to 50 addresses you already trust (address book, past counterparties): catches vanity "dust attack" look-alikes with the same first and last c…Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "compare": 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
    Compare a destination address with up to 50 addresses you already trust (address book, past counterparties): catches vanity "dust attack" look-alikes with the same first and last characters. Verdict exact_match / lookalike / partial / no_match. PAID: $0.001 per call or 1 prepaid credits, no account. Pay with x402 over MCP (USDC on Base), or with a credits key bought by a plain USDC transfer (credits_quote / credits_claim, then header Authorization: Bearer ssk_...). An unpaid call returns the payment terms and charges nothing; bad input is rejected before any payment; failed work is never charged. Same data as GET /v1/poison-check.

    Annotations the server declares

    • title: Address-poisoning look-alike check against addresses you trust
    • 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.
Can send data out2
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.

Findings

Matches of fixed checks, with the text they matched.

3 warn
  • The server marks "screen_payout_recipient_list" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "screen_payout_recipient_list" says "payout": a word that usually means money moves, which cannot be taken back.

    What this check looks for
  • The server marks "check_crypto_address_before_sending" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.recipient): what it sends cannot be taken back.

    What this check looks for
  • The server marks "payment_options" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "payment_options" says "payment": a word that usually means money moves, which cannot be taken back.

    What this check looks for

History

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

  1. Tools1 added.+1 addedView diff
  2. Tools1 added, 1 changed.+1 added~1 changedView diff

Install

Pinned to version 1.8.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http safe-send-check https://safe-send-check.agent-arena-base.workers.dev/mcp
claude mcp add --transport http safe-send-check https://safe-send-check.agent-arena-base.workers.dev/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__safe-send-check__detect_address_poisoning_lookalike"
    ],
    "ask": [
      "mcp__safe-send-check__screen_wallet_ofac_sanctions",
      "mcp__safe-send-check__screen_payout_recipient_list",
      "mcp__safe-send-check__check_crypto_chat_message_for_scams",
      "mcp__safe-send-check__sweep_crypto_chat_messages_for_scams",
      "mcp__safe-send-check__triage_crypto_support_ticket",
      "mcp__safe-send-check__check_crypto_address_before_sending",
      "mcp__safe-send-check__payment_options",
      "mcp__safe-send-check__credits_quote",
      "mcp__safe-send-check__credits_claim",
      "mcp__safe-send-check__credits_balance"
    ],
    "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 safe-send-check. Review it before you use it.

Capability tags behind 10 rules
  • mcp__safe-send-check__screen_wallet_ofac_sanctions untrusted-input
  • mcp__safe-send-check__screen_payout_recipient_list untrusted-input, outbound
  • mcp__safe-send-check__check_crypto_chat_message_for_scams untrusted-input
  • mcp__safe-send-check__sweep_crypto_chat_messages_for_scams untrusted-input
  • mcp__safe-send-check__triage_crypto_support_ticket untrusted-input
  • mcp__safe-send-check__check_crypto_address_before_sending untrusted-input, outbound
  • mcp__safe-send-check__detect_address_poisoning_lookalike untrusted-input
  • mcp__safe-send-check__credits_quote untrusted-input
  • mcp__safe-send-check__credits_claim untrusted-input
  • mcp__safe-send-check__credits_balance 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/dev.workers.agent-arena-base.safe-send-check/safe-send-check/verify?hash=721754f2ae38732982e66ea2fd3194b028923b82b4afe799ccae4f66e9a0fbaa" | jq -e '.changed == false'

Pinned hash 721754f2ae38, from Nov 21, 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/dev.workers.agent-arena-base.safe-send-check/safe-send-check/changes.xml

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

Badge

Anlyon Radar badge for dev.workers.agent-arena-base.safe-send-check/safe-send-check
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.agent-arena-base.safe-send-check/safe-send-check.svg)](https://radar.anlyon.com/servers/dev.workers.agent-arena-base.safe-send-check/safe-send-check)

Source: MCP Registry. Synced Nov 21, 2026, 14:18 UTC.

Safe-Send Check: crypto support triage, sanctions and scam screening MCP server: questions and answers

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

Is the Safe-Send Check: crypto support triage, sanctions and scam screening MCP server safe?

No scan can promise that. What its definitions show: 11 tools, 10 of which can change, send or delete something, and 3 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 Safe-Send Check: crypto support triage, sanctions and scam screening MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Safe-Send Check: crypto support triage, sanctions and scam screening MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: screen_payout_recipient_list, check_crypto_address_before_sending and payment_options.

What tools does the Safe-Send Check: crypto support triage, sanctions and scam screening MCP server have?

11 tools: 3 irreversible, 7 write, 1 read. screen_payout_recipient_list, check_crypto_address_before_sending, payment_options, screen_wallet_ofac_sanctions, check_crypto_chat_message_for_scams, sweep_crypto_chat_messages_for_scams, triage_crypto_support_ticket, credits_quote and 3 more.

Does the Safe-Send Check: crypto support triage, sanctions and scam screening MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): screen_payout_recipient_list and check_crypto_address_before_sending.

Has the Safe-Send Check: crypto support triage, sanctions and scam screening MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.