## Security model

Agen for SaaS operates on a **zero-trust** security model. Every request from an AI agent is treated as potentially untrusted and must pass through multiple verification and enforcement layers before reaching your APIs.

### Zero-trust principles

| Principle | Implementation |
|  --- | --- |
| **Verify explicitly** | Every request must include a valid authentication token. No implicit trust based on network location. |
| **Least-privilege access** | Tools are only accessible to users with explicitly assigned roles or permissions via access control rules. |
| **Assume breach** | All actions are logged, all sensitive data is masked, and all critical operations require human approval. |


### Identity and authentication

- All requests must include a valid JWT issued by your configured auth provider (Frontegg or OIDC).
- JWTs are validated on every request — expired, malformed, or unsigned tokens are rejected.
- The authorization server federation URL provides the endpoint for token validation.
- Custom domains can be configured for both authentication and MCP Gateway endpoints.


### Multi-tenant isolation

- Each tenant's data and policy context is isolated.
- JWT claims (tenant ID, roles, permissions) drive all access control and policy decisions.
- Tenant-level policy delegation allows customers to add their own governance within platform boundaries.
- Global policies set by the platform provider cannot be overridden by tenant-level policies.


### Backend verification

Agen for SaaS signs requests forwarded to your backend APIs with cryptographic signatures (SHA-256 HMAC). This allows your backend to verify that requests originate from your MCP Gateway and have not been tampered with.

For implementation details, see [Backend trust and verification](/agen-for-saas/configuration/backend-verification).

### Defense-in-depth layers

Requests pass through the following layers in order:

1. **TLS encryption** — All communication is encrypted in transit.
2. **Authentication** — Token validation and identity verification.
3. **Access control** — Role and permission-based tool restrictions.
4. **Policies** — Conditional rule evaluation (deny, step-up, approval).
5. **Hooks** — Custom code execution for additional validation.
6. **Data protection** — Sensitive data masking in responses.
7. **Monitoring** — Complete audit trail of the entire interaction.


### Related topics

- [Security and compliance overview](/agen-for-saas/security-compliance/overview)
- [Best practices](/agen-for-saas/security-compliance/best-practices)
- [Backend trust and verification](/agen-for-saas/configuration/backend-verification)
- [Access control](/agen-for-saas/access-control/overview)