Skip to content

cerberus-index MCP server

com.cerberusindex/cerberus-indexcerberusindex.comstreamable-httpv1.0.0Scanned

XRPL token rug-checks, issuer reputation & AMM data for AI agents. Pay-per-call USDC via x402.

20 tools: 14 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 14 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 1
  • 2 findings, 1 high

Tools listed without sign-in. Remote posture

With Anlyon

14 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 cerberus-index MCP server can do

The cerberus-index MCP server is published by cerberusindex.com, a domain the MCP Registry verified. It has 20 tools. It can create or change data (14 tools: check_xrpl_token, check_issuer_reputation, check_address, check_transaction and 10 more), but cannot delete data. 6 tools only read.

1 tool can send data out of your system (check_endpoint).

The fixed checks matched 2 findings, 1 of them high severity (model-directed-text and tool-shadowing). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 12, 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.

20 tools

Changes things 14Claude Code: ask
  • check_addressCross-chain address & counterparty risk — one call before you send to, approve, or trust an address.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
    Cross-chain address & counterparty risk — one call before you send to, approve, or trust an address. EVM chains (ethereum, base, bsc, polygon, arbitrum, optimism, avalanche, …): sanctions, mixer, phishing, drainer, money-laundering & cybercrime flags aggregated from GoPlus, told whether it's a contract or a wallet. XRP Ledger (r-addresses): Cerberus's own engine — the production rug blocklist, live clawback/global-freeze flags (can this address seize or freeze tokens it issues?), burn-address detection, and prior launch history — coverage no incumbent offers. Chain is auto-detected; pass `chain` to pick the EVM network (default ethereum). Verdict: high_risk | caution | safe | unknown, source named. Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.
  • check_alertsCollect alerts raised by your `watch_token` watches: what changed, how severe (critical | warning | info), and the on-chain numbers behind it — plus the status of every watch you o…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
    Collect alerts raised by your `watch_token` watches: what changed, how severe (critical | warning | info), and the on-chain numbers behind it — plus the status of every watch you own. Requires the `subscriber_key` from watch_token. Each alert is delivered once. FREE — poll it as often as every couple of minutes.
  • check_endpointEndpoint & tool trust — one call before an agent connects to a third-party MCP server or HTTP tool.Can send data out1 finding

    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.

    Findings

    • High

      The description contains "don't tell the user", an instruction to keep something from the user.

      Matched text

      description: "...hijack agents — instruction overrides, 'don't tell the user', data exfiltration, secret harvesting,..."

      What this check looks for
    Description, as the server wrote it
    Endpoint & tool trust — one call before an agent connects to a third-party MCP server or HTTP tool. Pass the endpoint `url` (and, to unlock the strongest check, its `tools`: the name/description/inputSchema the agent is about to trust). Returns three signals behind one verdict: (1) transport & TLS identity — encrypted, valid chain, not expired or self-signed; (2) domain age via RDAP — freshly-registered hosts are a scam tell; (3) a TOOL-POISONING scan of the tool definitions for the hidden directives that hijack agents — instruction overrides, 'don't tell the user', data exfiltration, secret harvesting, tool-shadowing, and invisible-unicode / homoglyph steganography that a human reviewer can't see. Nobody else screens tool descriptions for injection. Verdict: trusted | caution | untrusted | unknown, with per-finding evidence. Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.
  • check_issuer_reputationReputation for an XRPL issuer: blocklist status + historical detection outcomes.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
    Reputation for an XRPL issuer: blocklist status + historical detection outcomes. Price: $0.002 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • check_transactionSimulate an unsigned XRPL transaction and tell you what it will ACTUALLY do — before you sign it.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
    Simulate an unsigned XRPL transaction and tell you what it will ACTUALLY do — before you sign it. Pass the transaction JSON; get back (1) its intent in plain language, (2) a live-ledger dry-run (`simulate`): would it succeed, and the exact balance changes per account — computed, never submitted, never signed — and (3) drain vectors flagged: handing over your signing key (SetRegularKey / SignerListSet), disabling your master key, enabling clawback, partial-payment tricks, trustlines to blocklisted issuers, sends to flagged addresses. Verdict: danger | caution | safe | unknown. A transaction that would fail on-chain is reported as such. Price: $0.010 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.
  • check_xrpl_tokenLive safety verdict for an XRPL token: clawback & global-freeze hard rejects, issuer blackhole status (can supply ever be re-minted?), NoFreeze, pool depth & trading fee, LP-burn f…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
    Live safety verdict for an XRPL token: clawback & global-freeze hard rejects, issuer blackhole status (can supply ever be re-minted?), NoFreeze, pool depth & trading fee, LP-burn fraction (is liquidity locked?), plus Cerberus's proprietary rug blocklist & detection history. Verdicts: unsafe | caution | likely_safe | unknown, with reasons. Covers BOTH XRPL fungible-token standards. `currency` may be a 3-char or 40-char hex trust-line code, OR a 48-char MPTokenIssuanceID — pass an issuance ID and the token is screened as a Multi-Purpose Token instead (issuance locked, clawback, freeze power, allow-listing, transferability, mint headroom and transfer fee), with `issuer` ignored because the issuance ID already identifies it. Price: $0.005 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.
  • explore_tokensDiscover XRPL tokens — a DexScreener-style feed over 160k+ tokens.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
    Discover XRPL tokens — a DexScreener-style feed over 160k+ tokens. Rank by `sort` (volume_24h | marketcap | holders | trustlines | price), `query` to search by name, `limit`/`offset` to page, `trust_only` for XRPLMeta-trusted only. Each row returns name, icon, USD price, 24h volume, market cap, holder count, XRPLMeta trust level, AND our rug-blocklist flag — discovery with a trust signal built in. Run check_xrpl_token on any row for the full verdict. Price: $0.004 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • quote_ammQuote an XRP->token swap against the live XLS-30 AMM pool: tokens out, spot vs effective price, price impact.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
    Quote an XRP->token swap against the live XLS-30 AMM pool: tokens out, spot vs effective price, price impact. Price: $0.001 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • submit_feedbackRequest a tool/feature or report an issue.No findings

    Why it is in this group

    • The name "submit_feedback" says "submit": a word for a change.
    Description, as the server wrote it
    Request a tool/feature or report an issue. FREE. High-volume requests get built first — this is how you shape Cerberus's roadmap.
  • token_holdersHolder distribution & concentration risk for an XRPL token: holder count, top-1 and top-10 share of circulating supply, AMM pool excluded from whale math.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
    Holder distribution & concentration risk for an XRPL token: holder count, top-1 and top-10 share of circulating supply, AMM pool excluded from whale math. Flags single-wallet dump risk. Best for newer tokens (large tokens report 'unknown_large' honestly rather than guessing). Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • verify_attestationVerify a signed Cerberus attestation (from any tool called with `attest=true`).1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Warn

      The description names a tool "with" that this server does not list.

      Matched text

      description: "...a signed Cerberus attestation (from any tool called with `attest=true`). Recomputes the canonica..."

      What this check looks for
    Description, as the server wrote it
    Verify a signed Cerberus attestation (from any tool called with `attest=true`). Recomputes the canonical claim and checks the Ed25519 signature against this server's published key. Returns valid true/false with the claim. FREE — and you can verify independently with the public key at /api/attestation; this is a convenience, not a trust bottleneck.
  • verify_issuer_domainBidirectional domain verification for an XRPL issuer: decodes the on-chain Domain field and checks the domain's /.well-known/xrp-ledger.toml actually claims the issuer back.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
    Bidirectional domain verification for an XRPL issuer: decodes the on-chain Domain field and checks the domain's /.well-known/xrp-ledger.toml actually claims the issuer back. verified true/false with reasons — a strong legitimacy signal (its absence is a yellow flag). Price: $0.003 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • verify_priceCross-chain value truth for an XRPL token — 'is the price real?' Reconstructs the token's USD price on XRPL (XRPLMeta price × live XRP/USD) and checks it two ways: for a stablecoin…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
    Cross-chain value truth for an XRPL token — 'is the price real?' Reconstructs the token's USD price on XRPL (XRPLMeta price × live XRP/USD) and checks it two ways: for a stablecoin, whether the PEG still holds (is USDC actually ~$1 here?); for any cross-chain asset, whether the XRPL price has DIVERGED from its canonical price elsewhere (manipulation, stale liquidity, or arbitrage). Weighs it against real 24h volume — a price on a dead pool is a number, not a market. Verdict: price_consistent | price_divergent | depegged | thin_liquidity | native_no_reference | unknown. Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.
  • watch_tokenMonitor an XRPL token you hold and get alerted when it turns dangerous.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
    Monitor an XRPL token you hold and get alerted when it turns dangerous. A one-time check can't catch a rug that happens later — this watches the chain continuously for: AMM pool destroyed (completed rug), liquidity drained past your threshold, clawback enabled, global freeze set, issuer un-blackholed (supply re-mintable), issuer blocklisted, LP lock weakened. Returns a `subscriber_key` — STORE IT — then poll `check_alerts` (free). Registration is refused (with the reason) for tokens that are ALREADY compromised — blocklisted, clawback-enabled, frozen, or a husk pool — since those need a verdict now, not monitoring later. Sold as packages by monitoring window (`duration_days`): 1d $0.005 · 3d $0.012 · 7d $0.020 · 14d $0.035 · 21d $0.048 · 30d $0.060 USDC (longer = cheaper per day). The x402 payment demand lists every tier; pay the one you want and the watch length is set by what you pay. Calling again renews (extends) the watch. Missing something? Call `submit_feedback` (free) to request it.
Only reads 6Show 6 read-only tools
  • analyze_token_trendA data-driven technical read on an XRPL token.No findings

    Why it is in this group

    • The name "analyze_token_trend" says "analyze": a word for reading.
    Description, as the server wrote it
    A data-driven technical read on an XRPL token. Computes real indicators from OHLC — trend (9/21 EMA), RSI momentum, support/resistance, volatility, volume trend — with a plain-language assessment, and (when the server has an LLM configured) an AI-written outlook plus a genuine counter-argument. `interval` is 5|15|60|240|D|W, `bars` how many candles. Returns `ai_available` so you know whether the narrative is live. Always an informational signal, NEVER financial advice or a price target. Price: $0.020 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • find_best_pathFind the safest EXECUTABLE route to acquire an XRPL token and screen every hop.No findings

    Why it is in this group

    • The name "find_best_path" says "find": a word for reading.
    Description, as the server wrote it
    Find the safest EXECUTABLE route to acquire an XRPL token and screen every hop. Unlike quote_amm (one direct AMM pool), this asks the ledger for real payment paths (order books + AMM + multi-hop) and runs the rug-safety engine over every issuer and gateway the route touches — a clean token reached through a hop that can freeze or claw back mid-route is a trap a destination-only check misses. Returns the cheapest route, its effective price, hop count, and a verdict: route_safe | route_caution | route_unsafe | no_route, with the risk on each hop. Pass your `account` for routes specific to your trustlines, or omit it for an indicative route. Price: $0.006 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • get_new_poolsRecently detected XRPL AMM pools (newest first, max 100), enriched: readable name, age, initial liquidity and fee, plus an honest launch-time screening label.No findings

    Why it is in this group

    • The name "get_new_pools" says "get": a word for reading.
    Description, as the server wrote it
    Recently detected XRPL AMM pools (newest first, max 100), enriched: readable name, age, initial liquidity and fee, plus an honest launch-time screening label. Price: $0.010 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • get_token_ohlcOHLC price-history candles for an XRPL token — open/high/low/close plus volume per interval, the series behind a candlestick chart.No findings

    Why it is in this group

    • The name "get_token_ohlc" says "get": a word for reading.
    Description, as the server wrote it
    OHLC price-history candles for an XRPL token — open/high/low/close plus volume per interval, the series behind a candlestick chart. `interval` is 5 | 15 | 60 | 240 | D | W (minutes, or Day/Week); `bars` is how many candles (max 1000); prices are quoted in XRP, or pass `fx="USD"` for USD. Sourced from the XRPL DEX/AMM; returns ok:false with a reason when the pair is unknown or the source is unreachable — never invented prices. Price: $0.004 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • get_wallet_activityA readable, risk-annotated history of what an XRPL wallet did: recent transactions turned into plain language (sent/received amounts with token names, trustlines, DEX/AMM ops), wit…No findings

    Why it is in this group

    • The name "get_wallet_activity" says "get": a word for reading.
    Description, as the server wrote it
    A readable, risk-annotated history of what an XRPL wallet did: recent transactions turned into plain language (sent/received amounts with token names, trustlines, DEX/AMM ops), with counterparties on the Cerberus rug blocklist flagged, new trustlines to blocklisted issuers flagged, and account-takeover transactions (SetRegularKey, SignerListSet, master-key disable) surfaced as notable — watching your OWN wallet is compromise detection. Returns XRP balance, a summary (in/out counts, distinct and flagged counterparties, notable events), and a `marker` to page further back. Read-only. Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it.
  • resolve_assetCross-chain identity for an XRPL token — 'what is this, everywhere it exists?' Resolves the token's real identity across chains and catches IMPOSTORS: a token using a famous symbol…No findings

    Why it is in this group

    • The name "resolve_asset" says "resolve": a word for reading.
    Description, as the server wrote it
    Cross-chain identity for an XRPL token — 'what is this, everywhere it exists?' Resolves the token's real identity across chains and catches IMPOSTORS: a token using a famous symbol (USDC, WBTC, SOLO…) from an issuer that is NOT that asset's canonical deployment is flagged — a fake USDC is a fake USDC on every chain, and a single-chain check misses it. Combines XRPLMeta (the XRPL registry: name, issuer, trust_level), CoinGecko (the canonical multi-chain asset and every chain it lives on), and Cerberus's rug blocklist. Verdict: verified_crosschain | native_xrpl | impostor_suspected | unverified | unknown. Price: $0.008 USDC. Missing something? Call `submit_feedback` (free) to request it. Pass `attest=true` to also get an Ed25519-SIGNED attestation of this verdict — portable proof you can log, hand to a counterparty, or verify later with `verify_attestation` (free) or the published key.

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 or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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 20, 2026, 18:35 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
14
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 14 tools that change things (14 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://cerberusindex.com/mcp: tools/list returned 20 tools to an anonymous client, including check_xrpl_token (write), check_issuer_reputation (write), check_address (write), check_transaction (write), check_endpoint (write) and 9 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 high1 warn
  • The description contains "don't tell the user", an instruction to keep something from the user.

    Matched text

    description: "...hijack agents — instruction overrides, 'don't tell the user', data exfiltration, secret harvesting,..."

    What this check looks for
  • The description names a tool "with" that this server does not list.

    Matched text

    description: "...a signed Cerberus attestation (from any tool called with `attest=true`). Recomputes the canonica..."

    What this check looks for

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 cerberus-index https://cerberusindex.com/mcp
claude mcp add --transport http cerberus-index https://cerberusindex.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__cerberus-index__resolve_asset",
      "mcp__cerberus-index__get_new_pools",
      "mcp__cerberus-index__get_token_ohlc",
      "mcp__cerberus-index__get_wallet_activity",
      "mcp__cerberus-index__analyze_token_trend",
      "mcp__cerberus-index__find_best_path"
    ],
    "ask": [
      "mcp__cerberus-index__check_xrpl_token",
      "mcp__cerberus-index__check_issuer_reputation",
      "mcp__cerberus-index__check_address",
      "mcp__cerberus-index__check_transaction",
      "mcp__cerberus-index__check_endpoint",
      "mcp__cerberus-index__token_holders",
      "mcp__cerberus-index__verify_issuer_domain",
      "mcp__cerberus-index__verify_price",
      "mcp__cerberus-index__explore_tokens",
      "mcp__cerberus-index__quote_amm",
      "mcp__cerberus-index__watch_token",
      "mcp__cerberus-index__check_alerts",
      "mcp__cerberus-index__verify_attestation",
      "mcp__cerberus-index__submit_feedback"
    ],
    "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 cerberus-index. Review it before you use it.

Capability tags behind 1 rule
  • mcp__cerberus-index__check_endpoint 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/com.cerberusindex/cerberus-index/verify?hash=25bc0c796366a22b3ca0137edb494797b5211fcdfbc40099af9d78b37dd6acc6" | jq -e '.changed == false'

Pinned hash 25bc0c796366, from Nov 12, 2026, 21:17 UTC.

Watch

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

https://radar.anlyon.com/servers/com.cerberusindex/cerberus-index/changes.xml

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

Badge

Anlyon Radar badge for com.cerberusindex/cerberus-index
[![Anlyon Radar](https://radar.anlyon.com/badge/com.cerberusindex/cerberus-index.svg)](https://radar.anlyon.com/servers/com.cerberusindex/cerberus-index)

Source: MCP Registry. Synced Oct 21, 2026, 17:52 UTC.

cerberus-index MCP server: questions and answers

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

Is the cerberus-index MCP server safe?

No scan can promise that. What its definitions show: 20 tools, 14 of which can change, send or delete something, and 2 findings (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the cerberus-index MCP server delete data?

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

Can the cerberus-index 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 cerberus-index MCP server have?

20 tools: 14 write, 6 read. check_xrpl_token, check_issuer_reputation, check_address, check_transaction, check_endpoint, token_holders, verify_issuer_domain, verify_price and 12 more.

Does the cerberus-index MCP server need sign-in or OAuth?

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

Does the cerberus-index MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_endpoint.

Has the cerberus-index MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.