Skip to main content

NeuralTrust Documentation - AI Agent Security

Protect what your agents access and execute: models, tools, MCP servers, skills, and data, from one runtime layer.

This site is the API reference and setup guide for NeuralTrust. TrustGate is the gateway in front of models, tools, and MCP servers; TrustGuard evaluates that traffic at runtime; TrustTest runs adversarial probes against the same stack.

Start from an agent or provider below, or open a product guide when you already know which primitive you need.

Three primitives, one control plane

Use one product or all three. They share organization settings, not a single request path.

TrustGate

Agent Gateway

Connect agents to models and tools securely

Create a gateway

TrustGuard

Agent Runtime Security

Protect agent interactions in real time

Connect a collector

TrustTest

AI Red Teaming

Test your models with adversarial attacks

Run an evaluation