zunivo-mcp
Officialzunivo-mcp
Give your AI agent working money on Arc.
An MCP server that lets any MCP client (Claude, ChatGPT, Cursor, Gemini — anything that speaks MCP)
discover .agent services, pay for APIs over x402 in USDC, and issue payment
links — non-custodial, with a hard daily budget.
Tools
tool | what it does |
|
|
| public directory of callable |
| call a paid API — 402 handled, USDC paid within budget, receipt returned |
| invoice anyone: returns a pay URL |
| order status + settling payments |
| 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 hard daily budget (ZUNIVO_DAILY_CAP, default 5 USDC). SetZUNIVO_SPEND_FILE(e.g.~/.zunivo-spend.json) so the budget survives restarts — strongly recommended before pointing this at real funds.Content returned by paid endpoints is untrusted input to your model. A malicious API could try to talk your agent into more paid calls — the daily cap is the backstop; keep it small.
When paying a
.agentname, the recipient is pinned to the address the name 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 AI agents on Arc.