io.github.GuardBee/threat-rules·Security

threat-rules

GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection

Stars
1
Version
0.2.1
License
—
Review
Passed
Source npm
Language
TypeScript
Last commit
24m ago
Forks
1
Open issues
2
Registry update
Oct 13, 2026
ai-securitykvkkmcpmcp-securitymodel-context-protocolowaspsecurity-scanner

Connect

npm
Terminal
$claude mcp add threat-rules \  -- npx -y @guardbee/[email protected]

Environment variables

Nothing to configure — it works as is.

Security review

Review passed

Reviewed 43m ago.

metadata
scanned
packages
1 checked

No findings.

Tools

This server runs on your machine, so its tool list is not fetched before install — the README below describes what it offers.

README

GuardBee/guardbee-mcp/packages/threat-rules/README.md

@guardbee/mcp-threat-rules

🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇧🇷 Português | 🇪🇸 Español | 🇩🇪 Deutsch

GuardBee MCP bridge to Agent Threat Rules (ATR) — the open, Sigma-like detection standard for AI agent threats (prompt injection, tool poisoning, context exfiltration, MCP attacks).

ATR evaluates runtime events. GuardBee’s other packages mostly scan source/catalogs. This package connects both: run ATR plus GuardBee rules (KVKK / Turkish & Chinese injection / Chinese ID / lethal-trifecta intent), then jump to the matching GuardBee auditor.

Custom project rules: drop YAML into .guardbee/atr-rules/ or set GUARDBEE_ATR_RULES_DIR.

Telemetry on by default (tool name + short params; scanned content never leaves — see @guardbee/mcp-telemetry). Disable with GUARDBEE_TELEMETRY=0.

Claude ──► threat-rules (ATR) ──► matches + GuardBee follow-up hints
              │
              ├─ evaluate_text / evaluate_file / evaluate_event
              ├─ list_rules / rule_stats
              └─ explain_bridge

Built-in GuardBee rules include KVKK TC Kimlik, Turkish & Chinese injection, Chinese national ID, and lethal-trifecta intent (GB-ATR-2026-00001 … 00005).

Upstream ATR is MIT-licensed and already used across the industry. We depend on agent-threat-rules rather than forking it.

Tools

ToolPurpose
evaluate_textScore free text against ATR + GuardBee rules
evaluate_fileScore a local file
evaluate_eventScore a structured ATR AgentEvent JSON
list_rulesList loaded rules (source=atr|guardbee)
rule_statsCounts by category/source
explain_bridgeHow ATR maps onto GuardBee scanners

CLI

npx @guardbee/mcp-threat-rules eval "…" --format=json --fail-on=high
npx @guardbee/mcp-threat-rules scan ./prompt.txt --format=sarif
npx @guardbee/mcp-threat-rules list --source=guardbee
npx @guardbee/mcp-threat-rules stats

Related GuardBee packages

ATR categoryGuardBee follow-up
prompt-injection@guardbee/mcp-prompt-injection-scanner
tool-poisoning@guardbee/mcp-tool-poisoning-scanner
context-exfiltration@guardbee/mcp-toxic-flow-auditor, @guardbee/mcp-prompt-leak-scanner
privilege-escalation@guardbee/mcp-oauth-auditor, @guardbee/mcp-server-auditor

From the server's repository — third-party content, read it before running anything it suggests.

More in Security

attack-surface-mcp-server

io.github.cyanheads

Passive external attack-surface mapping: CT subdomains, DNS, TLS, HTTP posture, RDAP/WHOIS, Shodan.

security-suite

io.github.GuardBee

Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence

elicitation-auditor

io.github.GuardBee

MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs

secret-scanner

io.github.GuardBee

Scans files for leaked secrets and API keys

owasp-scan

io.github.GuardBee

Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF

prompt-injection-scanner

io.github.GuardBee

Scans RAG content/scraped pages for indirect prompt injection

Listing from the official MCP Registry · repository facts from GitHub, 13m ago.