MCP server

Ai Guardrails

io.github.lazymac2x/ai-guardrails

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Cloudflare Workers MCP server: ai-guardrails

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

5

Token cost

About 425 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.ai-guardrails]
url = "https://api.lazy-mac.com/ai-guardrails/mcp"

Gemini CLI

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

Cursor

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

VS Code

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

Antigravity

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

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"ai-guardrails","server_url":"https://api.lazy-mac.com/ai-guardrails/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"ai-guardrails","server_url":"https://api.lazy-mac.com/ai-guardrails/mcp"}

Tools

• check_hallucination ~73 tokens
  Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
• check_safety ~72 tokens
  Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).
• detect_pii ~80 tokens
  Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.
• full_check ~114 tokens
  Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.
• redact_pii ~86 tokens
  Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].

Browse

• GitHub tools
• Cloudflare tools
• Email
• GitHub and code hosting
• Cloud and hosting
• Calling other AI models

Related MCP servers

• Embedding Search
  Cloudflare Workers MCP server: embedding-search
• Cloudflare
  Cloudflare MCP servers
• OnPage.dev
  Free SEO MCP that closes the loop: find, fix, ship as a PR or to a CMS, prove. 37 tools, no key.
• Domain Intel
  Cloudflare Workers MCP server: domain-intel
• Interactive Api Playground
  Cloudflare Workers MCP server: interactive-api-playground
• Ai Gateway
  Cloudflare Workers MCP server: ai-gateway
• AINumbers Fintech Intelligence Suite
  754 MCP tools across 1221 fintech tools: ChainGraph AP2 decisions, execution_hash. Zero PII.
• Ai Cost Optimizer
  Cloudflare Workers MCP server: ai-cost-optimizer

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.lazymac2x/ai-guardrails.svg)](https://aptlynx.net/servers/io.github.lazymac2x/ai-guardrails)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents