Ai Guardrails

io.github.lazymac2xPublished by GitHub account lazymac2xv1.0.0Updated Oct 24, 2026

Cloudflare Workers MCP server: ai-guardrails

VerifiedStreamable HTTPWeb executableSecurity & MonitoringAI & ML

Overview

AI-generated overview

A remote MCP server that lets an assistant detect and redact personal data, score text for harmful content, and flag likely hallucination phrasing.

What you can do
Detect personal data such as email, phone, SSN, credit card, IP, URL and API key in a text string, and redact it by masking or typed placeholders like [EMAIL]. Score text for harmful content with weighted keyword detection, returning a 0–1 score and a safe, caution or unsafe verdict. Heuristically score LLM hedge phrases that correlate with hallucinated output, returning a 0–1 score and risk level. Run personal-data, safety and hallucination checks together in one call, defaulting to personal data plus safety.
When to use it
Useful when an assistant handles user-supplied or model-generated text and you want a quick pre-check before sharing, storing or acting on it, or when you want a lightweight sanity check on model output.
Requirements
A remote endpoint at over streamable HTTP. No authentication, environment variables or headers are declared, and no local package is needed.
Before you install
Text you submit is sent to a third-party remote service, so avoid sending sensitive or confidential content. Detection is keyword and heuristic based, so results can miss real personal data or harmful content and can flag harmless text; treat verdicts as advisory, not a compliance guarantee.

Installation

In SourceWeft

  1. Open Ai Guardrails in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.lazymac2x%2Fai-guardrails/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

README

This repository has no README.

Tools

5

detect_pii

Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.

Parameterstextrequired

redact_pii

Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].

Parametersmodetextrequired

check_safety

Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).

Parameterstextrequired

check_hallucination

Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.

Parameterstextrequired

full_check

Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.

Parameterstextrequiredchecks

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.