nidhipati — proof of spend for AI agents
Proof-of-spend and reserve checks for AI agents: receipts, spend audit, NAV, reconciliation.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"nidhipati": {
"url": "https://rta.lat/nidhipati/mcp"
}
}
}远程端点
https://rta.lat/nidhipati/mcpstreamable-http它能做什么
工具清单
工具(5)
🟢verify_receipt(receipt, public_key)
Check a signed proof-of-spend receipt offline: schema, Ed25519 signature, mandate expiry, positive amount, quantity*unit_price == amount, refund not above payment. Use when an agent or provider returns a receipt and you need to know whether it actually proves the charge was allowed. Do NOT use to move funds or to confirm a transaction on-chain - nothing here reads a chain.
输入模式
{
"type": "object",
"properties": {
"receipt": {
"type": "object",
"description": "The receipt document as JSON."
},
"public_key": {
"type": "string",
"description": "Ed25519 public key, base64url (from keygen) or 64 hex chars."
}
},
"required": [
"receipt",
"public_key"
]
}🟢audit_spend(records, policy)
Find duplicates, price escalation, failed-but-billed calls, runaway loops, missing refunds, model overpay, unknown asset/network and budget breaches in a list of settled agent calls. Returns three separate amounts (money without a basis, estimate above the agent's own median, budget overrun) instead of one sum, because adding them together would overstate what can be recovered. Do NOT use as a statement of money actually returned.
输入模式
{
"type": "object",
"properties": {
"records": {
"type": "array",
"description": "Rows with ts, agent_id, tool, quote, settled, status; optional model, actual, refund, asset, network, tx_hash, payee.",
"items": {
"type": "object"
}
},
"policy": {
"type": "object",
"description": "Optional budget policy: {\"limit_usd\": \"100\"}."
}
},
"required": [
"records"
]
}🟢reserve_report(reserve)
Turn an issuer's reserve lines into a NAV with explicit formulas and a sha256 evidence hash per line. Verdict is backed, underbacked, or incomplete - and the backing ratio is refused (null) when any line has no price, because a ratio over half a reserve is not a number. Do NOT treat the result as a statutory audit.
输入模式
{
"type": "object",
"properties": {
"reserve": {
"type": "object",
"description": "Reserve document."
}
},
"required": [
"reserve"
]
}🟢resolve_report(market)
Weigh the sources a resolver says it read against the declared outcome. Verdicts: supported, disputed, single_source, insufficient. A conflict is reported as a conflict, never averaged. Do NOT use to trade or to place a position.
输入模式
{
"type": "object",
"properties": {
"market": {
"type": "object",
"description": "Market document."
}
},
"required": [
"market"
]
}🟢reconcile_books(invoices, transactions)
Match invoices to stablecoin transfers by memo first, then exact amount and asset inside the invoice window. Names what is left over in both directions: invoices nobody paid, money nobody invoiced, invoices paid twice. A duplicate is counted once, never twice. Do NOT use as proof of who the payer was.
输入模式
{
"type": "object",
"properties": {
"invoices": {
"type": "array",
"items": {
"type": "object"
},
"description": "id, amount, asset, created_at; optional due_at, payee, memo."
},
"transactions": {
"type": "array",
"items": {
"type": "object"
},
"description": "tx_hash, amount, asset, timestamp; optional to, memo."
}
},
"required": [
"invoices",
"transactions"
]
}社区
证据