OpenAI-compatible proxy that adds PII redaction, prompt-injection blocking, spend caps and SSO/SIEM to LLM and MCP calls.
What it does
AI Security Gateway is an OpenAI-compatible proxy that sits between an app and any LLM provider to enforce governance. It redacts PII, blocks prompt injections, caps spend, smart-routes to the cheapest provider and adds SSO, SIEM connectors and hybrid-VPC deployment, plus an MCP gateway for agent tool calls.
Core features
DLP redaction of 30+ PII types
Prompt-injection blocking and agent loop detection
Per-project hard budget caps and smart routing
SAML SSO and SIEM connectors
MCP gateway and hybrid-VPC/on-prem deployment
Best for
→Enforcing PII/HIPAA/PCI compliance on AI calls
→Controlling and reducing multi-provider LLM cost
→Governing what data developers send to LLMs
→Securing agent tool calls over MCP
Pricing
Managed Credits
$0/mo
Starter BYOK
$9/mo
Pro BYOK
$29/mo
Reviews
Big-picture takes: what it's for and whether it delivers. High-engagement YouTube videos — not sponsored.
Tutorials
Step-by-step: exactly how to get things done with it.