scamgate runs on your own machine — the client starts it, so there is no endpoint to ping. 475 installs a week from pypi. Last commit 1 Nov 2026.
Offline scam check for agents: verify links and payments before acting (allow, ask or deny).
Today is the operative word: we check scamgate 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 scamgate -- uvx scamgate
{
"mcpServers": {
"scamgate": {
"command": "uvx",
"args": [
"scamgate"
]
}
}
}
[mcp_servers.scamgate]
command = "uvx"
args = ["scamgate"]
{
"mcpServers": {
"scamgate": {
"command": "uvx",
"args": [
"scamgate"
]
}
}
}
{
"servers": {
"scamgate": {
"type": "stdio",
"command": "uvx",
"args": [
"scamgate"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SCAMGATE_AUTO_UPDATE (Set to 1 to refresh the phishing lists every 6 hours while the server runs (off by default)), SCAMGATE_URLHAUS_AUTH_KEY (Optional abuse.ch Auth-Key that adds the URLhaus malware-link list).
Verified directory for machine payments (x402 & MPP): check services and wallets before agents pay.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Policy decision point for agent payments — allow, ask, or veto before signing
Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.
Allow, ask, or veto — a policy decision point your agent consults before signing any payment
Stripe payments for AI agents. Create links, verify, manage customers.
Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.
Pre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.
Answers built from our own checks of this server.