Threat Rules runs on your own machine — the client starts it, so there is no endpoint to ping. 362 installs a week from npm. Last commit 2 Nov 2026.
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
Nothing serious here today
Today is the operative word: we check Threat Rules every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 threat-rules -- npx -y @guardbee/mcp-threat-rules{
"mcpServers": {
"threat-rules": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-threat-rules"
]
}
}
}[mcp_servers.threat-rules]
command = "npx"
args = ["-y", "@guardbee/mcp-threat-rules"]{
"mcpServers": {
"threat-rules": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-threat-rules"
]
}
}
}{
"servers": {
"threat-rules": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-threat-rules"
]
}
}
}Alternatives to Threat Rules
same job, measured the same waySecurity scanning and threat detection for AI agents
A harness for driving a Godot 4 project from an agent: addons, runtime bridge, MCP server, CLI.
Agent-to-agent communication bridge for multi-agent systems
The API-change deploy gate for AI coding agents. Read-only breaking-change detection.
Constitutional guardrails and loop detection for AI agents
Laviya AI Orchestration MCP runtime for IDE and agent integrations.
Amazon review mining for AI agents — complaint detection, sentiment trends, complaint topics.
Routes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.
Threat Rules — questions
Answers built from our own checks of this server.