UXUS Agent Services: wallet lookup, entity labels, caller ID

io.github.Dcroyalty由 GitHub 帳號 Dcroyalty 發布v1.4.0更新於 Oct 24, 2026

Free wallet lookup, ENS, labels, caller ID. Paid x402: search, scrape, XRP yield and lending grades

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取金融安全與監控

概覽

AI 產生的概覽

遠端 MCP 伺服器，用於加密錢包篩查：地址查詢、ENS/Basenames 解析、實體標籤、來電判定，以及付費的網頁搜尋與擷取。

可以做什麼
  • 查詢 Ethereum、Base 與 XRPL 地址，自動辨識鏈別
  • 雙向解析 ENS 與 Basenames 名稱，反向紀錄經正向驗證
  • 判定地址所屬類別，例如交易所、混幣器、詐騙或受制裁
  • 判斷錢包訊息應回覆、篩查還是封鎖，並附上理由
  • 為付費網頁搜尋、頁面擷取以及 XRP 收益與借貸風險評級回傳付款資源
  • 檢查服務健康狀態
適用情境
適合助理在採取行動前查核加密地址或錢包，例如查看標籤、制裁或詐騙類別、解析名稱、過濾錢包訊息。也適合想按次付費使用網頁搜尋、擷取或 XRP 收益與借貸風險評級、又不想註冊帳號的代理。
執行需求
遠端 streamable HTTP 端點位於 uxus.finance；未宣告需要帳號、API 金鑰或註冊。付費工具需要已儲值的錢包，透過 x402 協定在 Base 上以 USDC 付款。需要能連線至該服務的網路。
安裝前請注意
多個工具按次以 Base 上的 USDC 收費，使用時會從所連結的錢包支出真實資金。搜尋與擷取工具只回傳付款資源，本身不執行操作。風險結論是基於公開資料的開發者級篩查，不構成法律或合規建議；資料不可用時評分會失敗開放為 CAUTION。免費工具會把查詢的地址傳送給第三方服務。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 UXUS Agent Services: wallet lookup, entity labels, caller ID，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Dcroyalty%2Fuxus/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "uxus-agent-services-wallet-lookup-entity": {
      "type": "http",
      "url": "https://uxus.finance/api/mcp"
    }
  }
}

README

UXUS — Agent Services

Pay-per-call primitives for AI agents, live at uxus.finance. Paid in USDC on Base via the x402 protocol — no accounts, no API keys, no signup. A funded wallet is the whole integration.

Services

EndpointPriceWhat you get
POST /api/llm$0.01LLM completion, 5-model fallback chain
GET /api/scrape$0.01URL → clean markdown/text/html
POST /api/extract$0.01messy text/URL → JSON in your schema
POST /api/embed$0.01text → 1024-dim vectors (jina-embeddings-v3)
GET /api/search$0.01live web search
GET /api/risk/pro$0.02one call, one verdict: PROCEED / CAUTION / BLOCK + summary + reasons
GET /api/risk/live/pro$0.02one-call verdict on a token's owner powers (can it still be paused, upgraded or rugged?) + reasons
GET /api/risk · /api/risk/livefreerisk score + verdict (no reasons/signals)
GET /api/lookupfreeaddress lookup for Ethereum, Base and XRPL, chain auto-detected
GET /api/entityfreeentity attribution — what is this address
GET /api/resolvefreeENS / Basenames, forward + reverse (forward-verified)
GET /api/calleridfreeshould this wallet be answered? (for XMTP/Push)
/api/shield/*freeper-user private wallet blocklist (signature-auth)
GET /api/catalog · /openapi.json · /llms.txt · /.well-known/x402.jsonfreediscovery
POST /api/mcpfreeMCP server (Streamable HTTP) over the free tools

Every risk/verdict response carries a disclaimer: this is developer-grade screening from public data (OFAC SDN list, community scam registries, on-chain reads), not legal or compliance advice.

Data

  • Sanctions come from one place: the OFAC SDN list in bad_addresses (source='ofac'), refreshed daily by /api/cron/refresh-lists (guarded — a 0-address upstream response aborts rather than wiping the table). lib/entity.ts is the only place that joins it. A non-OFAC blocklist hit is category flagged, not sanctioned, and is allowlistable.
  • Scoring fails open: if a data source needed for a verdict is unavailable and there's no list hit, the response is degraded:true / verdict CAUTION, never PROCEED.

Development

bash
npm installnpm run dev        # http://localhost:3000npm run build

Env (Vercel project settings):

varrequiredpurpose
DATABASE_URLyesNeon Postgres
CRON_SECRETyesgates /api/cron/*; Vercel Cron sends it as Authorization: Bearer
OPENROUTER_API_KEYfor /api/llm, /api/extract
JINA_API_KEYfor /api/embed
SERPER_API_KEY / BRAVE_API_KEYoptional/api/search (falls back to DuckDuckGo)
ETHERSCAN_API_KEYoptionalwallet history (falls back to Blockscout)
CDP_API_KEY_ID / CDP_API_KEY_SECRETfor x402 settlement

Scripts: scripts/schema*.mjs (create tables), scripts/ingest*.mjs (manual list load — the scheduled path is lib/refresh-lists.ts + scripts/ingest-entity.mjs), scripts/shield-verify.mjs (live E2E), scripts/fix-sanctions.mjs (one-shot sanctions remediation, already run).

來源：README.md，提交 27b53f9

工具

9

search_web

Live web search: ranked results plus Google's answer box, knowledge graph, people-also-ask and related searches when the Google-backed provider answers. This is a PAID x402 call: $0.01 USDC on Base at GET /api/search. This tool returns the payment resource to call; it does not run the search. Params: query (string, required); count (integer 1-20, default 10); country/language/page/device (optional).

輸入參數pagecountquery必填devicecountrylanguage

scrape_url

Any web page as clean, LLM-ready markdown, text or html. This is a PAID x402 call: $0.01 USDC on Base at GET /api/scrape. This tool returns the payment resource to call; it does not fetch the page. Params: url (absolute http/https URL, required); format (markdown | text | html, default markdown); max_chars (integer, default 40000, max 120000).

輸入參數url必填formatmax_chars

yield_grade

A-F risk grade for one way to earn on XRP or RLUSD, from the XRP Yield Desk (xrplhub.io/yield): XRPL AMM pools, Doppler vaults, Firelight stXRP and other Flare FXRP products, RLUSD and XRP DeFi pools, and exchange earn programs. Returns the rate, size, lockup and withdrawal terms, who holds the keys, chain, age, audits, the data source with its timestamp, and every rule that moved the grade. General information, not advice; the products graded pay nothing. This is a PAID x402 call: $0.02 USDC on Base at GET /api/yield/grade. This tool returns the payment resource to call; it does not compute the grade. Find ids for free at https://www.xrplhub.io/api/yield/options. Params: id (option id, required).

輸入參數id必填

lending_grade

A-F risk grade for one XRP Ledger lending vault or loan broker, from on-ledger data only (size, utilization, first-loss cover ratio, late/impaired/defaulted loans, unrealized loss, realized yield), with every rule that moved the grade. Not a credit rating. This is a PAID x402 call: $0.02 USDC on Base at GET /api/lending/grade. This tool returns the payment resource to call; it does not compute the grade. NOT LIVE YET: it goes live when XRPL lending (the LendingProtocol and SingleAssetVault amendments) is enabled on mainnet. Until then this tool returns available:false and GET /api/lending/grade returns 503 with no charge. Params: id (64-hex Vault or LoanBroker ID, required); type (vault | broker, optional).

輸入參數id必填type

lookup_wallet

Address lookup for Ethereum and Base 0x addresses and XRPL r-addresses, auto-detected. Params: address (EVM 0x address or XRPL classic r-address, required); chain (optional EVM history hint: base default, or ethereum). Detects EVM vs XRPL from the format. Returns one normalized envelope: { address, chain, chain_detected, exists, risk_score, risk_level, verdict, flags, entity, name }. Free. For a fast first-pass check on a counterparty wallet.

輸入參數chainaddress必填

resolve_name

Bidirectional name <-> address resolution for ENS (name.eth) and Basenames (name.base.eth). Param: q (an ENS/Basename name, an EVM 0x address, or an XRPL r-address, required). Auto-detects direction. Reverse records are forward-verified against the address to stop name spoofing. Returns { query, kind, namespace, chain, resolved, address, name, sources }. XRPL .xrp names are detected but resolved:false (no canonical registry). Free.

輸入參數q必填

check_entity

Entity attribution — what IS this address, not who owns it. Params: address (0x EVM address, required); chain (base default, or ethereum). Returns { address, chain, is_known, label, category }. category is one of sanctioned, mixer, exchange, bridge, dex_router, scam, drainer, phishing, flagged, token_contract, protocol, unknown. "sanctioned" is set only when the address is on the OFAC SDN list (the same source /api/risk uses); a non-OFAC blocklist hit is "flagged". Sourced from OFAC, ScamSniffer, MEW, eth-labels and curated Base/Tornado sets. Never guesses. Free.

輸入參數chainaddress必填

caller_id

Should this wallet be answered? For wallet messaging (XMTP, Push), which has no spam filter. Params: address (0x EVM address, required); chain (base default, or ethereum). Composes entity attribution + risk score + on-chain history + forward-verified name into ANSWER | SCREEN | BLOCK with reasons[] and a confidence flag. BLOCK on sanctioned/drainer/phishing/scam/mixer or risk verdict BLOCK; SCREEN is the default for unknown addresses. Free.

輸入參數chainaddress必填

health

Service health check. No parameters. Returns { ok, service, time, upstream } — confirms the uxus.finance API is reachable. Free.

無需輸入參數。

版本歷史

3
  1. v1.4.0最新Oct 16, 2026
  2. v1.3.0Oct 16, 2026
  3. v1.2.0Oct 12, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。