
Ai Guardrails
The source repository is essentially empty with no documentation, so here's what we know: this is a Cloudflare Workers-based MCP server hosted at api.lazy-mac.com that apparently provides AI guardrails functionality. It uses streamable HTTP transport, which means it can handle streaming responses. Without a readme or code visibility, it's unclear what specific guardrails it implements, whether it's content filtering, prompt injection detection, rate limiting, or something else entirely. If you need AI safety controls and are willing to rely on an external API endpoint, this might be worth exploring, but you'll need to test the actual endpoints to see what operations are available since the repository provides no documentation about capabilities or usage.
- tools
- 5
- transport
- HTTP
- last updated
- May 16, 2026
Install
From registry metadata$ npx add-mcp https://api.lazy-mac.com/ai-guardrails/mcp --name ai-guardrailsRun in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.
Review the command, arguments and environment values before installing. MCP servers run with your local permissions.
Other ways
Claude Code
$ claude mcp add --transport http ai-guardrails https://api.lazy-mac.com/ai-guardrails/mcpRun in your terminal. Add --scope user to make it available in every project.
Tools
Verified live · 5 toolsVerified live against the running server on Nov 6, 2026.
detect_piiDetect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.1 params
Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.
text*stringredact_piiRedact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].2 params
Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].
modestringmask · tagdefault: masktext*stringcheck_safetyCheck text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).1 params
Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).
text*stringcheck_hallucinationHeuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.1 params
Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
text*stringfull_checkRun pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.2 params
Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.
checksarraytext*stringSponsors
Readme
Details
- Repository
- github.com/lazymac2x/ai-guardrails-api
- Category
- Cloud & Infrastructure
- Transport
- HTTP
- Registry
- MCP registry, active
- Tools verified
- Nov 6, 2026
More from lazymac2x
- Ai Model Router
- Ai Prompt Optimizer
- Ai Provider Status
- Ai Rate Limit Tracker
- Ai Token Counter
- Api Changelog Tracker
- Api Composition Gateway
- Api Contract Validator
- Api Diff Monitor
- Api Flow Analyzer
- Api Payload Auditor
- Api Perf Analyzer
- Api Request Deduplicator
- Api Response Cost Analyzer
- Api Schema Drift Detector
- Blog
- Citation Verifier
- Claude Skill Validator
- Code Explainer
- Code Pattern Risk Scanner
- Color Palette
- Cron Collision Detector
- Cron Monitor
- Cron Parser