Skip to content

nulucre-wallet-reputation MCP server

io.github.vjshaw/nulucre-wallet-reputationvjshawstreamable-httpv1.1.0Scanned

Wallet trust scores for AI agents. Stellar, XRPL, EVM 81+ chains. OFAC sanctions. x402 payments.

5 tools: 5 only read.

Tools: 0 delete, 0 irreversible, 0 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • 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 nulucre-wallet-reputation MCP server can do

The nulucre-wallet-reputation MCP server is published by the GitHub account vjshaw. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

5 tools bring in text other people can write (nulucre_get_stellar_wallet_score, nulucre_get_evm_wallet_score, nulucre_get_solana_wallet_score and 2 more).

The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.1.0.

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.

5 tools

Only reads 5Show 5 read-only tools
  • nulucre_check_service_statusCheck whether the live Nulucre reputation oracle service is online.Reads text others writeNo findings

    Why it is in this group

    • The name "nulucre_check_service_status" says "status": 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
    Check whether the live Nulucre reputation oracle service is online. This is a free endpoint that requires no payment. Use this tool to verify Nulucre is reachable before relying on it for wallet scoring decisions, or for general uptime monitoring. Args: none Returns: Structured data with schema: { "status": string, // "online" if the service is reachable "service": string // service name } Examples: - Use when: "Is Nulucre up?" -> no params needed - Use when: checking service availability before a batch of scoring calls Error Handling: - Returns "Error: ..." with details if the service is unreachable

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • nulucre_get_evm_wallet_scoreGet a 0-100 trust score for an EVM wallet address (0x...) from Nulucre, a multi-chain wallet reputation oracle covering 81+ chains.Reads text others writeNo findings

    Why it is in this group

    • The name "nulucre_get_evm_wallet_score" 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 a 0-100 trust score for an EVM wallet address (0x...) from Nulucre, a multi-chain wallet reputation oracle covering 81+ chains. The score is computed from on-chain data including wallet age, transaction volume, DeFi activity, and multi-chain presence, pulled from Etherscan, Moralis, Alchemy, and Ankr. Use this tool to assess counterparty risk before an agent interacts with or pays an EVM wallet on Ethereum, Base, Polygon, Arbitrum, Optimism, or any of the 81+ supported chains. Args: - wallet (string): EVM wallet address starting with '0x' (42 characters) - signed (boolean): If true, request an ECDSA-P256 signed score for independent verification via Nulucre's public JWKS endpoint (default: false) - response_format ('markdown' | 'json'): Output format (default: 'markdown') Returns: For JSON format: Structured data with schema: { "wallet": string, "score": number, // 0-100 "status": string, // TRUSTED | VERIFIED | CAUTION | RISKY | BLACKLISTED "breakdown": { "<signalName>": { "score": number, "raw": string }, ... }, "chains"?: string[], "dataSource": string, "timestamp": string, "signature"?: string // present only when signed=true } Examples: - Use when: "Is this Ethereum wallet trustworthy?" -> wallet="0xabc...", signed=false - Use when: "Get a verifiable score for this 0x address" -> wallet="0xabc...", signed=true - Don't use when: scoring a Stellar G... address (use nulucre_get_stellar_wallet_score instead) Error Handling: - Returns "Error: Invalid EVM wallet address" if the address format is invalid - Returns a payment-required explanation if the free evaluation quota is exhausted

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • nulucre_get_solana_wallet_scoreGet a 0-100 trust score for a Solana wallet address from Nulucre.Reads text others writeNo findings

    Why it is in this group

    • The name "nulucre_get_solana_wallet_score" 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 a 0-100 trust score for a Solana wallet address from Nulucre. Scored using 7 native Solana RPC signals: account age, transaction volume, SOL balance, token diversity, recent activity, program account status, and failed transaction ratio. Includes real-time OFAC/UN/EU sanctions screening. Use before paying or interacting with any Solana wallet. Pay per query via x402 USDC micropayments.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • nulucre_get_stellar_wallet_scoreGet a 0-100 trust score for a Stellar wallet address (G...) from Nulucre, a live Stellar-native wallet reputation oracle.Reads text others write1 finding

    Why it is in this group

    • The name "nulucre_get_stellar_wallet_score" 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.

    Findings

    • Info

      The description is 2,750 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...Returns a payment-required explanation if the free evaluation quota is exhausted"

      What this check looks for
    Description, as the server wrote it
    Get a 0-100 trust score for a Stellar wallet address (G...) from Nulucre, a live Stellar-native wallet reputation oracle. The score is computed from 8 signals pulled directly from the Stellar Horizon API and Stellar Expert — account age, transaction volume, asset diversity, SDEX DEX participation, network trust, claimable balance activity, Soroban contract interactions, and liquidity pool participation, plus a spam detection penalty. No EVM data is used. Every score includes a real-time sanctions screening result against the OFAC SDN, OFAC Non-SDN, EU Financial Sanctions, and UN Security Council Sanctions lists. A wallet matching any of these lists automatically receives a score of 0 and status BLACKLISTED. Use this tool to assess counterparty risk before an agent interacts with or pays a Stellar wallet — for example before executing a payment, approving a swap counterparty, or evaluating a new account. Args: - g_address (string): Stellar wallet address starting with 'G' (56 characters) - signed (boolean): If true, request an ECDSA-P256 signed score for independent verification via Nulucre's public JWKS endpoint (default: false) - response_format ('markdown' | 'json'): Output format (default: 'markdown') Returns: For JSON format: Structured data with schema: { "wallet": string, "network": "stellar:pubnet", "score": number, // 0-100 "status": string, // TRUSTED | VERIFIED | CAUTION | RISKY | BLACKLISTED "breakdown": { "accountAge": { "score": number, "raw": string }, "txVolume": { "score": number, "raw": string }, "assetDiversity": { "score": number, "raw": string }, "dexParticipation": { "score": number, "raw": string }, "networkTrust": { "score": number, "raw": string }, "claimableActivity": { "score": number, "raw": string }, "sorobanUsage": { "score": number, "raw": string }, "liquidityPools": { "score": number, "raw": string }, "spamPenalty": { "score": number, "raw": string }, "sanctionsCheck": { "score": number, "raw": "CLEAR"|"SANCTIONED"|"UNCHECKED", "source": string } }, "dataSource": string, "timestamp": string, "signature"?: string // present only when signed=true } Examples: - Use when: "Is this Stellar wallet safe to pay?" -> g_address="GABC...", signed=false - Use when: "Get a verifiable score I can check independently" -> g_address="GABC...", signed=true - Don't use when: scoring an Ethereum or other EVM address (use nulucre_get_evm_wallet_score instead) Error Handling: - Returns "Error: Invalid Stellar wallet address" if the address format is invalid - Returns a payment-required explanation if the free evaluation quota is exhausted

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • nulucre_get_xrpl_wallet_scoreGet a 0-100 trust score for an XRPL wallet address (r...) from Nulucre.Reads text others writeNo findings

    Why it is in this group

    • The name "nulucre_get_xrpl_wallet_score" 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 a 0-100 trust score for an XRPL wallet address (r...) from Nulucre. Scored using 7 XRPL Ledger signals: account age, transaction volume, trustline diversity, DEX participation, network trust, payment activity, and spam detection. Includes real-time OFAC/UN/EU sanctions screening. Use before paying or interacting with any XRPL wallet.

    Annotations the server declares

    • 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 or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write5
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 20, 2026, 19:12 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
0
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

Findings

Matches of fixed checks, with the text they matched.

1 info

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

claude mcp add --transport http nulucre-wallet-reputation https://agents.nulucre.com/mcp
claude mcp add --transport http nulucre-wallet-reputation https://agents.nulucre.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__nulucre-wallet-reputation__nulucre_get_stellar_wallet_score",
      "mcp__nulucre-wallet-reputation__nulucre_get_evm_wallet_score",
      "mcp__nulucre-wallet-reputation__nulucre_get_solana_wallet_score",
      "mcp__nulucre-wallet-reputation__nulucre_get_xrpl_wallet_score",
      "mcp__nulucre-wallet-reputation__nulucre_check_service_status"
    ],
    "ask": [],
    "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 nulucre-wallet-reputation. Review it before you use it.

Capability tags behind 5 rules
  • mcp__nulucre-wallet-reputation__nulucre_get_stellar_wallet_score untrusted-input
  • mcp__nulucre-wallet-reputation__nulucre_get_evm_wallet_score untrusted-input
  • mcp__nulucre-wallet-reputation__nulucre_get_solana_wallet_score untrusted-input
  • mcp__nulucre-wallet-reputation__nulucre_get_xrpl_wallet_score untrusted-input
  • mcp__nulucre-wallet-reputation__nulucre_check_service_status 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/io.github.vjshaw/nulucre-wallet-reputation/verify?hash=8d162b8a068a7e5151c2e2733bd956f0400543b81a080819ef7ea1e74358a691" | jq -e '.changed == false'

Pinned hash 8d162b8a068a, from Nov 20, 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/io.github.vjshaw/nulucre-wallet-reputation/changes.xml

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

Badge

Anlyon Radar badge for io.github.vjshaw/nulucre-wallet-reputation
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.vjshaw/nulucre-wallet-reputation.svg)](https://radar.anlyon.com/servers/io.github.vjshaw/nulucre-wallet-reputation)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:51 UTC.

nulucre-wallet-reputation MCP server: questions and answers

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

Is the nulucre-wallet-reputation MCP server safe?

No scan can promise that. What its definitions show: 5 tools, all of which only read, and 1 finding from fixed checks. Read-only tools can still pass private data to a model.

Can the nulucre-wallet-reputation MCP server delete data?

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

Can the nulucre-wallet-reputation 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 nulucre-wallet-reputation MCP server have?

5 tools: 5 read. nulucre_get_stellar_wallet_score, nulucre_get_evm_wallet_score, nulucre_get_solana_wallet_score, nulucre_get_xrpl_wallet_score and nulucre_check_service_status.

Does the nulucre-wallet-reputation MCP server need sign-in or OAuth?

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

Does the nulucre-wallet-reputation MCP server send data to outside services?

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

Has the nulucre-wallet-reputation MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.