Skip to content

io.github.lazymac2x/ai-guardrails

by lazymac2x · remote · no sign-in to list tools · v1.0.0 · published by GitHub user lazymac2x

Cloudflare Workers MCP server: ai-guardrails

Changes · 5
CompareRegistry entry

5 tools: 5 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 5Claude Code: ask
  • check_hallucinationHeuristic scoring of LLM hedge phrases that correlate with hallucinated outputs.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
  • check_safetyCheck text for harmful content using weighted keyword detection.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).
  • detect_piiDetect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.
  • full_checkRun pii, safety, and/or hallucination checks in one call.No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.
  • redact_piiRedact PII from text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__ai-guardrails__detect_pii",
      "mcp__ai-guardrails__redact_pii",
      "mcp__ai-guardrails__check_safety",
      "mcp__ai-guardrails__check_hallucination",
      "mcp__ai-guardrails__full_check"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ai-guardrails. Review it before you use it.