LLM Red-Team Scanner
LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"llm-red-team-scanner": {
"url": "https://qdmbzzwftor2rgmxupyyasguhy.srv.us/mcp"
}
}
}遠端端點
https://qdmbzzwftor2rgmxupyyasguhy.srv.us/mcpstreamable-http它能做什麼
工具清單
工具（4）
⚪run_free_scan(spec)
Free LLM agent security review in ~35s. Two parts: (1) 8 live adversarial probes (jailbreak / prompt injection / system-prompt extraction / tool abuse) against your agent spec, and (2) a deterministic static audit of which guardrails the spec text itself is missing. Returns a 0-100 risk score, per-finding evidence, and a paste-ready guardrail sentence for each gap.
輸入結構描述
{
"type": "object",
"properties": {
"spec": {
"type": "string",
"description": "Your agent / system prompt (>=20 chars)"
}
},
"required": [
"spec"
]
}🟢get_scan_result(job_id)
Poll a scan by job id (returned by run_free_scan) until status=done.
輸入結構描述
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
}
},
"required": [
"job_id"
]
}🟢get_pricing
PRO pricing & payment info: 44 probes / 20 attack classes / 0-100 score / CI gate / per-class remediation, 0.15 XNO (ERC-20 or Lightning) or card.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_purchase_flow
Machine-readable autonomous purchase procedure: how an agent pays (0.15 XNO, or USDC on Base via x402) and receives the PRO download with no human in the loop (callback push + poll fallback).
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據