Skip to main content

Documentation Index

Fetch the complete documentation index at: https://cloudsineai-5cd7c547.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

The Protector Plus Guardrail Service API exposes two inspection endpoints — one for prompts (/input-check) and one for responses (/output-check) — plus an unauthenticated health probe.

​
Base URL

https://<your-protector-plus-host>
Your <your-protector-plus-host> depends on your deployment:
  • AWS Marketplace AMI — the public IP or DNS of your EC2 instance.
  • Kubernetes / Helm — the hostname exposed by your Ingress Controller.
  • On-prem — the hostname inside your network.

​
Authentication

All API calls require an API key passed in the X-API-Key header. See Authentication.

​
Content type

All endpoints accept application/json.

​
Endpoints

EndpointMethodPurpose
/apikey/api/protectorplus/v1/input-checkPOSTInspect a user prompt before forwarding to the LLM.
/apikey/api/protectorplus/v1/output-checkPOSTInspect an LLM response before returning to the user.
/api/protectorplus/v1/healthGETLiveness probe — no authentication.

​
Where to start

Authentication

Generate and use your API key.

Integration pattern

Wire input-check + output-check into your LLM call path.

input-check

Prompt inspection.

output-check

Response inspection.

Need an API key?

Request a sandbox key for evaluation or a deeper technical conversation.