# ai-guardrails MCP server

Cloudflare Workers MCP server: ai-guardrails

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-lazymac2x-ai-guardrails
- Repository: https://github.com/lazymac2x/ai-guardrails-api

## Install
- Endpoint: https://api.lazy-mac.com/ai-guardrails/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.lazy-mac.com/ai-guardrails/mcp

## Tools
- detect_pii - Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string. Endpoint: https://api.lazy-mac.com/ai-guardrails/mcp
- redact_pii - Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL]. Endpoint: https://api.lazy-mac.com/ai-guardrails/mcp
- check_safety - Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe). Endpoint: https://api.lazy-mac.com/ai-guardrails/mcp
- check_hallucination - Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level. Endpoint: https://api.lazy-mac.com/ai-guardrails/mcp
- full_check - Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all. Endpoint: https://api.lazy-mac.com/ai-guardrails/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.lazymac2x
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 16, 2026
- Source: https://registry.modelcontextprotocol.io