io.github.lazymac2x/ai-guardrails

up checked 2026-11-11T07:39:06.687Z

Unclaimed · Unverified

Publisher-provided description

Cloudflare Workers MCP server: ai-guardrails

Summary by lookupd

Lets an agent scan text for PII, score harmful content and hallucination risk, and redact personal data from strings.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http ai-guardrails https://api.lazy-mac.com/ai-guardrails/mcp

Codex, remote (streamable-http)

codex mcp add ai-guardrails --url https://api.lazy-mac.com/ai-guardrails/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "ai-guardrails": {
      "url": "https://api.lazy-mac.com/ai-guardrails/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.lazymac2x/ai-guardrails.svg)](https://lookupd.com/servers/io.github.lazymac2x/ai-guardrails)