Dregs is answering right now. Last checked 15 min ago. Last commit 24 Oct 2026.
Fraud and abuse detection for SaaS: investigate scored identities, triage escalations, tune rules.
Over the last week it answered 94.2% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.
claude mcp add dregs-mcp --transport http https://dregs.com/mcp
https://dregs.com/mcp
[mcp_servers.dregs-mcp]
url = "https://dregs.com/mcp"
{
"mcpServers": {
"dregs-mcp": {
"url": "https://dregs.com/mcp"
}
}
}
{
"servers": {
"dregs-mcp": {
"type": "http",
"url": "https://dregs.com/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://dregs.com/mcp | streamable-http | sign-in | 153 ms | 15 min ago |
Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.
Production security for Node.js apps: investigate live attacks, block IPs, tune detections.
Trust verification for agents and packages: safety scans, signed scores, identity and badges.
MCP server for Sift — global ML fraud detection: real-time risk scoring, decisions, event ingestion
Agent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents
Deep Research MCP for multi-round investigations, traceable evidence, and cited reports.
Manage incidents, on-call schedules, escalation policies, and alert notifications
Document fraud detection for manipulated, fake and AI-generated PDF and image documents.
Answers built from our own checks of this server.