zunivo-mcp
Give your AI agent working money on Arc.
An MCP server that lets any MCP client (Claude Desktop, Claude Code, etc.)discover .agent services, pay for APIs over x402 in USDC, and issue paymentlinks — non-custodial, with a hard daily budget.
Tools
| tool | what it does |
|---|---|
zunivo_resolve_agent |
.agent name → on-chain card (payout address, endpoint, records) |
zunivo_list_agents |
public directory of callable .agent services |
zunivo_paid_fetch |
call a paid API — 402 handled, USDC paid within budget, receipt returned |
zunivo_create_payment_link |
invoice anyone: returns a pay URL |
zunivo_check_order |
order status + settling payments |
zunivo_spend_status |
today's budget: cap, spent, remaining |
Safety model
- The private key lives in env — it is never shown to the model.
- Every call is capped (
ZUNIVO_MAX_PER_CALL, default 1 USDC) under a harddaily budget (ZUNIVO_DAILY_CAP, default 5 USDC). SetZUNIVO_SPEND_FILE(e.g.~/.zunivo-spend.json) so the budget survives restarts — stronglyrecommended before pointing this at real funds. - Content returned by paid endpoints is untrusted input to your model. Amalicious API could try to talk your agent into more paid calls — thedaily cap is the backstop; keep it small.
- When paying a
.agentname, the recipient is pinned to the address thename resolves to on-chain — a malicious server cannot redirect funds.
Setup (Claude Desktop)
{
"mcpServers": {
"zunivo": {
"command": "npx",
"args": ["-y", "zunivo-mcp"],
"env": {
"AGENT_PK": "0x<agent wallet private key>",
"ZUNIVO_RECORDS_ADDRESS": "0x<ZunivoAgentRecords on Arc>",
"ZUNIVO_DAILY_CAP": "5",
"ZUNIVO_MAX_PER_CALL": "1"
}
}
}
}
Fund the wallet with test USDC at https://faucet.circle.com (Arc Testnet).
Example session
You: find me a crypto index feed and get the latest value
Agent: lists agents → finds
data.agent→ paid_fetch/v1/index/crypto→ pays 0.05 USDC → returns the data + ArcScan receipt
Part of the Zunivo network — the payment layer for AIagents on Arc.
