UXUS Agent Services: wallet lookup, entity labels, caller ID
RemoteAbout UXUS Agent Services: wallet lookup, entity labels, caller ID
UXUS Agent Services provides pay-per-call services for AI agents, including wallet and entity lookup, risk screening, web search, scraping, and data processing. Free endpoints cover several lookup and MCP functions; paid calls use USDC on Base through x402 without accounts or API keys.
Key features
- 01Wallet lookup across Ethereum, Base, and XRPL
- 02ENS and Basenames resolution
- 03Entity attribution and caller ID
- 04Risk screening with verdicts
- 05Paid search, scraping, and data tools
Use cases
- 01Checking a wallet address and entity
- 02Screening token owner powers
- 03Searching or extracting information from the web
- 04Providing wallet blocklist and caller-ID checks
MCP support
A free `/api/mcp` endpoint provides an MCP server over the free tools, using Streamable HTTP.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://uxus.finance/api/mcpclaude mcp add --transport http dcroyalty-uxus https://uxus.finance/api/mcp{"mcpServers":{"dcroyalty-uxus":{"type":"http","url":"https://uxus.finance/api/mcp"}}}Open in Cursor{"servers":{"dcroyalty-uxus":{"type":"http","url":"https://uxus.finance/api/mcp"}}}Open in VS Code{"mcpServers":{"dcroyalty-uxus":{"type":"http","url":"https://uxus.finance/api/mcp"}}}{"mcpServers":{"dcroyalty-uxus":{"serverUrl":"https://uxus.finance/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
9| Parameter | Type | Required | Description |
|---|---|---|---|
| page | integer | No | 1-based result page. Optional. |
| count | integer | No | Number of results, 1-20. Default 10. |
| query | string | Yes | Search query. Required. |
| device | string | No | Forwarded to the upstream provider if set; not confirmed to change results on every provider. Optional. |
| country | string | No | 2-letter country code. Optional. |
| language | string | No | 2+ letter language code. Optional. |
Details
From the project READMEUXUS — 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
| Endpoint | Price | What you get |
|---|---|---|
POST /api/llm | $0.01 | LLM completion, 5-model fallback chain |
GET /api/scrape | $0.01 | URL → clean markdown/text/html |
POST /api/extract | $0.01 | messy text/URL → JSON in your schema |
POST /api/embed | $0.01 | text → 1024-dim vectors (jina-embeddings-v3) |
GET /api/search | $0.01 | live web search |
GET /api/risk/pro | $0.02 | one call, one verdict: PROCEED / CAUTION / BLOCK + summary + reasons |
GET /api/risk/live/pro | $0.02 | one-call verdict on a token's owner powers (can it still be paused, upgraded or rugged?) + reasons |
GET /api/risk · /api/risk/live | free | risk score + verdict (no reasons/signals) |
GET /api/lookup | free | address lookup for Ethereum, Base and XRPL, chain auto-detected |
GET /api/entity | free | entity attribution — what is this address |
GET /api/resolve | free | ENS / Basenames, forward + reverse (forward-verified) |
GET /api/callerid | free | should this wallet be answered? (for XMTP/Push) |
/api/shield/* | free | per-user private wallet blocklist (signature-auth) |
GET /api/catalog · /openapi.json · /llms.txt · /.well-known/x402.json | free | discovery |
POST /api/mcp | free | MCP 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.tsis the only place that joins it. A non-OFAC blocklist hit is categoryflagged, notsanctioned, 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/ verdictCAUTION, neverPROCEED.
Development
npm install
npm run dev # http://localhost:3000
npm run build
Env (Vercel project settings):
| var | required | purpose |
|---|---|---|
DATABASE_URL | yes | Neon Postgres |
CRON_SECRET | yes | gates /api/cron/*; Vercel Cron sends it as Authorization: Bearer |
OPENROUTER_API_KEY | for /api/llm, /api/extract | |
JINA_API_KEY | for /api/embed | |
SERPER_API_KEY / BRAVE_API_KEY | optional | /api/search (falls back to DuckDuckGo) |
ETHERSCAN_API_KEY | optional | wallet history (falls back to Blockscout) |
CDP_API_KEY_ID / CDP_API_KEY_SECRET | for 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).
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.