◈ SecuriX

Overview

How Securix works - at a glance

Securix sits between your AI agent and external services, handling authentication, security, and monitoring so you don't have to.

High-Level Flow

Your AI Agent → Securix Proxy → Google/Gmail/Drive/etc

            [Token Vault]

            [Security Rules]

            [User Dashboard]

What Securix Handles

  1. Authentication - OAuth with providers (Google, Microsoft, etc.)
  2. Token Storage - Vaults raw tokens securely
  3. Proxying - Forwards API requests with tokens injected
  4. MCP Gateway - Provides a secure Model Context Protocol interface for AI Agents
  5. Security - Applies user-defined rules and monitors for anomalies
  6. Monitoring - Provides dashboard for users to see agent activity

What You Handle

  1. Building your AI Agent - Your core logic
  2. Accessing User Data - Using your securix-api-key, securix-agent-id and the user's securix-entity-id
  3. Displaying Data - Showing results to users

Traditional OAuth vs Securix

AspectTraditional OAuthSecurix
Token StorageYour database (high risk)Securix Vault (encrypted)
User ControlAll-or-nothing revokeGranular (folder hide, read-only)
MonitoringNoneReal-time dashboard
Audit Costs$15K+/year (you pay)Included
VerificationYou need to verifyAlready verified

Key Terminology

TermDefinition
AASBAgent Access Security Broker - the architectural pattern
entityIdA unique identifier for the user's connection (the "Entity")
Token VaultSecuriX's encrypted storage for provider tokens
Virtual ScopesUser-defined permission overrides
Proxy LayerIntercepts requests, injects tokens, applies rules

Ready to Dive Deeper?

On this page