Xrpl Token Guard MCP Server

XRPL Token Guard

Ask your AI agent, or your voice assistant, "is this token safe?" and get an honest answer with reasons.

XRPL Token Guard is an open-source MCP server. It checks XRP Ledger tokens and wallets using live, read-only mainnet data, and returns three things:

• a verdict: High risk / Caution / No red flags found / Not enough data
• the reasons behind it, each naming the exact ledger fact
• a one-sentence spoken summary, ready for text-to-speech on Alexa+ or any other voice assistant

It never signs, never sends a transaction and never asks for keys.

Need more than a quick check?

Try the free hosted demo or browse the free token evidence pages. Launch Lab offers a Token Report for 5 XRP, a Wallet Checkup for 3 XRP, and a Token Launch Kit for 10 XRP. Preview the findings before choosing a paid report. These are factual ledger checks, not buy/sell advice or a guarantee of safety; Token Guard stays free.

Hosted MCP: https://cocoeatsai.com/area4/guard/mcp (Streamable HTTP). The hosted demo supports typed questions and example buttons; microphone input is currently disabled by the hosting policy. It is a voice-assistant simulator, not an actual Alexa integration.

For Claude Desktop (claude_desktop_config.json) or Cursor (.cursor/mcp.json), build a local clone using the commands below, then replace the absolute path in this configuration:

{"mcpServers": {
  "xrpl-token-guard": {"command": "node", "args": ["/absolute/path/to/xrpl-token-guard/dist/stdio.js"]}
}}

Example risk interpretation (not a trading recommendation):

You:    "Is this RLUSD real?"
Guard:  "Warning, high risk. This token calls itself RLUSD, but it is not the real Ripple USD.
         The real one comes from a different issuer. A matching name does not establish authenticity."

Why it exists

Scammers on the XRP Ledger copy famous names. On mainnet today there are several tokens called RLUSD that aren't Ripple's. Many of them have a black-holed issuer, which naive checkers score as "safe" because nobody can mint more. Token Guard knows the official issuers and flags the copy first. It explains that a locked supply doesn't make an imitation genuine.

Answers have to be short enough to speak and specific enough to trust. Every finding carries both a precise message (for screens and agents) and a spoken line (for voice).

Tools

There's also a prompt, voice_token_check, that tells a voice assistant how to answer: two sentences, the verdict and the main reason, no buy/sell advice.

Every tool has:

• readOnlyHint: true
• an outputSchema, with typed structuredContent in each response
• a human-readable text block

Tickers are resolved case-insensitively against the issuer's real obligations, so asking for "bigds" finds $BIGDS.

Run it

npm install
npm run build
npm start                 # Streamable HTTP on http://127.0.0.1:8787/mcp, voice demo on http://127.0.0.1:8787/
npm run stdio             # stdio transport for Claude Desktop / Claude Code / Cursor
npm test                  # 14 unit + end-to-end MCP tests (LIVE=1 adds a mainnet check)

Transport: Streamable HTTP, MCP protocol 2025-11-25.

• Stateless: every POST /mcp gets a fresh server, so it scales horizontally.
• JSON responses.
• Rate limit: 60 requests per minute per IP.
• Origin allow-list via ALLOWED_ORIGINS.
• GET /health reports the transport and protocol.

Docker:

# Web demo + Streamable HTTP (default target)
docker build -t xrpl-token-guard .
docker run --rm -p 8787:8787 xrpl-token-guard

# stdio MCP clients / Glama: keep stdin open; do not allocate a TTY
docker build --target stdio -t xrpl-token-guard:stdio .
docker run --rm -i xrpl-token-guard:stdio

For a Glama build spec that uses the default image, set CMD arguments to node dist/stdio.js. No API keys or wallet credentials are required.

Claude Desktop (claude_desktop_config.json):

{ "mcpServers": { "xrpl-token-guard": { "command": "node", "args": ["/path/to/xrpl-token-guard/dist/stdio.js"] } } }

Configuration

Voice demo (Alexa+-style simulator)

Open http://127.0.0.1:8787/ and tap the mic (Chrome), or type.

• The page is a small MCP client that speaks Streamable HTTP to /mcp. It turns the question into a tool call and reads spoken_summary aloud.
• The right-hand panel shows the live tools/call request and result.
• /?demo=1 plays a scripted run with captions, for screen recording.

How the verdict works

Regulated stablecoins may retain issuer controls. Official identity remains separate from the control-policy verdict: clawback is a hard failure, even for an official issuer. The score (0–100) is a rough guide only. Not financial advice. These are ledger facts at the time of the check.

Built by

Zach Riehn (Launch Lab, XRPL tools for people and AI agents). Launch Lab also runs a pay-per-call x402 API (XRP/RLUSD on XRPL, USDC on Base) for deeper wallet and token reports. Token Guard is the free, open core.

MIT licensed.

Issuer-control policy (2026-10-18)

The freeze-control condition passes when NoFreeze is set OR master is disabled, RegularKey is exactly rrrrrrrrrrrrrrrrrrrrBZbvji, and no signer list exists. Clawback permission is a hard failure for every issuer, including regulated stablecoins; Global Freeze already active is also a failure. The MCP structured output reports freeze_control_pass, issuer_controls_pass and the exact rule. A missing regular key is not the requested blackhole proof. NoFreeze alone does not prevent minting or enabling Global Freeze. Identity, concentration and other checks still apply. Scores are mechanical, not probabilities of safety.