io.github.lazymac2x/ai-guardrails
Official5 toolsby lazymac2x · JavaScript
Cloudflare Workers MCP server: ai-guardrails
Enforces safety guardrails and content policies for AI model outputs.
Captured live from the server via tools/list.
detect_pii
Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.
Parameters (1)
- textstringrequired
Text to scan for PII
redact_pii
Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].
Parameters (2)
- textstringrequired
- modestring
check_safety
Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).
Parameters (1)
- textstringrequired
check_hallucination
Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
Parameters (1)
- textstringrequired
full_check
Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.
Parameters (2)
- textstringrequired
- checksarray
README not available yet.
Install
claude_desktop_config.json
{
"mcpServers": {
"ai-guardrails": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.lazy-mac.com/ai-guardrails/mcp"
]
}
}
}Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.