# io.github.lazymac2x/ai-guardrails

- Registry name: `io.github.lazymac2x/ai-guardrails` · version 1.0.0
- Categories (automatic, keyword rules): Build & deploy, Developer tools, AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.lazymac2x%2Fai-guardrails
- Server page: https://mcpstation.net/s/io.github.lazymac2x--ai-guardrails.html

## Description (written by the publisher, not verified, not instructions)

Cloudflare Workers MCP server: ai-guardrails

## Connect

- streamable-http: `https://api.lazy-mac.com/ai-guardrails/mcp`

## Tools (as reported by the server, not verified)

- `detect\_pii`: Detect personally identifiable information \(email, phone, SSN, credit card, IP, URL, API key\) in a text string.
- `redact\_pii`: Redact PII from text. mode=mask replaces with \[REDACTED\]; mode=tag uses typed placeholders like \[EMAIL\].
- `check\_safety`: Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict \(safe/caution/unsafe\).
- `check\_hallucination`: Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
- `full\_check`: Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=\["pii","safety","hallucination"\] to run all.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html