ai-guardrails
Cloudflare Workers MCP server: ai-guardrails
我該用這個嗎
品質與安全性
發現項目(5)
- HIGH
- MEDIUM在 redact_pii 中
- LOW在 redact_pii 中
- LOW在 check_hallucination 中
- INFO在 redact_pii 中
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": {
"ai-guardrails": {
"url": "https://api.lazy-mac.com/ai-guardrails/mcp"
}
}
}遠端端點
https://api.lazy-mac.com/ai-guardrails/mcpstreamable-http它能做什麼
工具清單
工具(5)
⚪detect_pii(text)
Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to scan for PII"
}
},
"required": [
"text"
]
}⚪redact_pii(text, mode)
Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"mask",
"tag"
],
"default": "mask"
}
},
"required": [
"text"
]
}🟢check_safety(text)
Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
}
},
"required": [
"text"
]
}🟢check_hallucination(text)
Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
}
},
"required": [
"text"
]
}🟢full_check(text, checks)
Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"checks": {
"type": "array",
"items": {
"type": "string",
"enum": [
"pii",
"safety",
"hallucination"
]
},
"default": [
"pii",
"safety"
]
}
},
"required": [
"text"
]
}社群
證據