Skip to content

Safe or Scam MCP server

dev.workers.safe-or-scam.scam-check/safe-or-scamscam-check.safe-or-scam.workers.devstreamable-httpv2.0.0Scanned

Crypto scam checks (tokens, sites, wallets), chain reads, web page to Markdown, email checks.

8 tools: 4 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 4 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. 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 or Scam MCP server can do

The Safe or Scam MCP server is published by scam-check.safe-or-scam.workers.dev, a domain the MCP Registry verified. It has 8 tools. It can create or change data (4 tools: check_token, check_website, check_wallet and check_email), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (read_webpage); 2 tools can send data out of your system (check_website and read_webpage).

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 9, 2026, version 2.0.0.

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.

8 tools

Changes things 4Claude Code: ask
  • check_emailCheck an email address before sending or signing someone up: valid format, domain exists and accepts mail (MX), throwaway/disposable domain, typo suggestions (gmial.com → gmail.com…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.
    Description, as the server wrote it
    Check an email address before sending or signing someone up: valid format, domain exists and accepts mail (MX), throwaway/disposable domain, typo suggestions (gmial.com → gmail.com), role addresses (info@, support@), SPF/DMARC. Returns valid / risky / invalid with reasons.
  • check_tokenIs this crypto token a scam?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.
    Description, as the server wrote it
    Is this crypto token a scam? Honeypot buy/sell simulation, hidden taxes, mint/freeze authority, hidden owner, blacklist, whale concentration, liquidity lock. Returns red/yellow/green with reasons. EVM chains + Solana.
  • check_walletIs it safe to send crypto to this address, and is this wallet exposed?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.
    Description, as the server wrote it
    Is it safe to send crypto to this address, and is this wallet exposed? Checks scam, phishing, theft, sanctions and mixer links; risky or malicious token approvals (who can drain the wallet); contract vs personal wallet; brand-new 'poisoned' look-alike addresses. Returns red/yellow/green with reasons. EVM chains + Solana.
  • check_websiteIs this website a crypto scam or phishing page?Can 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.

    What it can reach

    • 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
    Is this website a crypto scam or phishing page? Phishing databases, domain age, look-alikes of 45+ crypto brands (MetaMask, Phantom, Binance...), seed-phrase requests, wallet-drainer code. Returns red/yellow/green with reasons.
Only reads 4Show 4 read-only tools
  • get_token_infoRead a token's on-chain details: name, symbol, decimals, total supply.No findings

    Why it is in this group

    • The name "get_token_info" says "get": a word for reading.
    Description, as the server wrote it
    Read a token's on-chain details: name, symbol, decimals, total supply. Solana: supply, decimals, mint authority and freeze authority.
  • get_transactionLook up a transaction by hash: success/failed/pending, confirmations, time, sender, receiver, value, fee, method, decoded token and NFT transfers, and token approvals it granted (f…No findings

    Why it is in this group

    • The name "get_transaction" says "get": a word for reading.
    Description, as the server wrote it
    Look up a transaction by hash: success/failed/pending, confirmations, time, sender, receiver, value, fee, method, decoded token and NFT transfers, and token approvals it granted (flags unlimited approvals). Solana: balance changes per account.
  • get_wallet_balancesGet a wallet's balances: native coin (ETH, BNB, POL, AVAX, SOL) and tokens.No findings

    Why it is in this group

    • The name "get_wallet_balances" says "get": a word for reading.
    Description, as the server wrote it
    Get a wallet's balances: native coin (ETH, BNB, POL, AVAX, SOL) and tokens. Solana: every SPL token held. EVM: popular tokens on the chain plus any token addresses you pass. Also returns transactions sent and whether the address is a contract.
  • read_webpageFetch any public web page and return clean Markdown of its main content (headings, lists, links, code), plus title and description.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_webpage" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe name "read_webpage" says "read" and "webpage": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "fetch" and "web": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetch any public web page and return clean Markdown of its main content (headings, lists, links, code), plus title and description. Strips menus, footers, ads and scripts so it is ready for an LLM. Not charged if the page can't be fetched.

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 write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
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.

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 18, 2026, 16:24 UTC, unchanged since Oct 27, 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
4
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
  • WarnThe whole server

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

    Matched text

    https://scam-check.safe-or-scam.workers.dev/mcp: tools/list returned 8 tools to an anonymous client, including check_token (write), check_website (write), check_wallet (write), check_email (write)

    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 2.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http safe-or-scam https://scam-check.safe-or-scam.workers.dev/mcp
claude mcp add --transport http safe-or-scam https://scam-check.safe-or-scam.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-or-scam__get_wallet_balances",
      "mcp__safe-or-scam__get_transaction",
      "mcp__safe-or-scam__get_token_info"
    ],
    "ask": [
      "mcp__safe-or-scam__check_token",
      "mcp__safe-or-scam__check_website",
      "mcp__safe-or-scam__check_wallet",
      "mcp__safe-or-scam__read_webpage",
      "mcp__safe-or-scam__check_email"
    ],
    "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-or-scam. Review it before you use it.

Capability tags behind 2 rules
  • mcp__safe-or-scam__check_website outbound
  • mcp__safe-or-scam__read_webpage untrusted-input, outbound

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.safe-or-scam.scam-check/safe-or-scam/verify?hash=c637e1c3ba980376c913fdc940911ee53289c5d563b69ca79c489aa7ceef2ab7" | jq -e '.changed == false'

Pinned hash c637e1c3ba98, from Nov 9, 2026, 17:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.workers.safe-or-scam.scam-check/safe-or-scam/changes.xml

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

Badge

Anlyon Radar badge for dev.workers.safe-or-scam.scam-check/safe-or-scam
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.safe-or-scam.scam-check/safe-or-scam.svg)](https://radar.anlyon.com/servers/dev.workers.safe-or-scam.scam-check/safe-or-scam)

Source: MCP Registry. Synced Oct 27, 2026, 18:17 UTC.

Safe or Scam MCP server: questions and answers

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

Is the Safe or Scam MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 4 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 Safe or Scam 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 or Scam MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Safe or Scam MCP server have?

8 tools: 4 write, 4 read. check_token, check_website, check_wallet, check_email, get_wallet_balances, get_transaction, get_token_info and read_webpage.

Does the Safe or Scam MCP server need sign-in or OAuth?

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

Does the Safe or Scam 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): check_website and read_webpage.

Has the Safe or Scam MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.