Walletbureau runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from npm. Last commit 14 Aug 2026.
Risk score for a Base wallet before your agent pays it: 0-100, verdict and explained flags.
Today is the operative word: we check Walletbureau 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 mcp -- npx -y @walletbureau/mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@walletbureau/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@walletbureau/mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@walletbureau/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@walletbureau/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
WALLETBUREAU_API_KEY (Prepaid WalletBureau API key (atk_...). Optional: without any credentials the server runs on the free demo quota.), X402_PRIVATE_KEY (Private key of a wallet holding USDC on Base to pay per call via x402. Optional; ignored when WALLETBUREAU_API_KEY is set.), X402_MAX_PRICE_USD (Spending cap per call in USD for x402 payments. Default: 0.1.).
The author declared them in the registry entry; get the values from the project itself.
Check an x402 endpoint before you pay it: verdict, risk score and what is wrong. $0.005 in USDC.
Trust layer for agent payments (x402, Base): verify agents, risk scores, signed escrow verdicts.
Score a planned spend before an agent pays. Verdicts: approve, ask_human, or block.
Verify before your agent acts on data it paid for. Signed verdicts, checkable offline, via x402.
Check any x402 endpoint before your AI agent pays it: trust grade, verdict, and hijack checks.
Reputation oracle for AI agents on Base: SAFE/CAUTION/BLOCK + 0-100 score before you pay. x402+MCP
Wash-traffic risk checks for Algorand x402 endpoints before your agent trusts or pays them.
Scan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents
Answers built from our own checks of this server.