Spend Guard runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 31 Oct 2026.
Budgets, payee allowlists, price-spike checks and human approval for agents paying x402 paywalls
Today is the operative word: we check Spend Guard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add spend-guard -- npx -y @vulinh1704/spend-guard
{
"mcpServers": {
"spend-guard": {
"command": "npx",
"args": [
"-y",
"@vulinh1704/spend-guard"
]
}
}
}
[mcp_servers.spend-guard]
command = "npx"
args = ["-y", "@vulinh1704/spend-guard"]
{
"mcpServers": {
"spend-guard": {
"command": "npx",
"args": [
"-y",
"@vulinh1704/spend-guard"
]
}
}
}
{
"servers": {
"spend-guard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vulinh1704/spend-guard"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SPEND_GUARD_POLICY (Policy JSON file: networks, budgets, approval amount, spike ratio, known services and their payees. Without one, every payment waits for your approval), SPEND_GUARD_RAILS (How to pay: mock (pays nothing), near, arc, gateway, or a comma list. arc and gateway need ARC_PRIVATE_KEY, near needs NEAR_ACCOUNT_ID and NEAR_PRIVATE_KEY), SPEND_GUARD_LEDGER (Decisions file, read back on start so a restart keeps today's spend; servers on one file share one budget. Default ~/.spend-guard/ledger.jsonl; off keeps it in memory), SPEND_GUARD_DASHBOARD_PORT (Port of the approval dashboard on 127.0.0.1. 0 picks a free one; off means no dashboard, and payments that need approval are declined), SPEND_GUARD_APPROVAL_TIMEOUT (Seconds a payment waits for your answer before it is declined. Raise it together with your client's tool timeout), SPEND_GUARD_MOCK_NETWORK (Network the mock rail pretends to pay on), ARC_PRIVATE_KEY (Agent key for the arc and gateway rails. Testnet keys only), NEAR_ACCOUNT_ID (Agent account for the near rail (testnet)), NEAR_PRIVATE_KEY (Agent key for the near rail. Testnet keys only).
Safety checks for AI agents paying on Base: free SpendGuard, paid x402 token risk and preflight.
Pre-spend trust for AI agents that buy: check x402 services and product listings before paying.
Pay for x402 paywalls, datasets, and store checkouts on Solana, behind hard spending caps.
AI agent payment security - spending limits, whitelists, and human approval.
Spending controls for AI agents: per-agent budgets, vendor allowlists, full audit trail.
Prepaid virtual cards for AI agents: one-time cards, spend caps, human approvals.
x402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial.
Let your AI agent pay x402 APIs within daily caps, allowed hosts and human approval.
Answers built from our own checks of this server.