Overview

Connect NeuralTrust to coding agents, agent platforms, AI gateways, agent frameworks, and applications

NeuralTrust integrates with the tools already in your AI stack, including coding agents, agent platforms, AI gateways, agent frameworks, and applications. Use this catalog to find the supported connection points and setup instructions for each tool.

Products

An integration may support TrustGuard, TrustGate, or both.

Product	Purpose	Integration capability
TrustGuard	Runtime security for prompts, responses, tool calls, and tool results. It returns an allow, report, transform, ask, or block verdict.	Applies policy to traffic at the integration point. The host tool enforces the verdict.
TrustGate	An AI gateway for model provider and MCP traffic.	Centralizes routing, credentials, rate limits, and in-flight payload transformation.

TrustGuard evaluates individual interactions. TrustGate controls how applications and agents reach model providers and MCP servers. Some coding-agent plugins configure both products.

Find your tool

AI coding agents

Developer tools and managed coding environments that can read repositories, execute commands, and call external tools.

TrustGuard lifecycle hooks and TrustGate MCP access are separate controls with separate credentials. The events available to TrustGuard and the way each verdict is enforced depend on the coding agent.

Tool	TrustGuard	TrustGate
Claude Code	Local lifecycle hooks evaluate prompts, tool calls, and tool results	An MCP endpoint for the CLI; organization-managed access is configured through Claude Enterprise
Cursor	A plugin evaluates prompts, tool calls, and tool results	Organization-managed MCP endpoint in place of per-machine server configuration
Codex	Lifecycle hooks evaluate prompts, shell commands, patches, and tool results	TrustGate MCP server configuration for the CLI, desktop app, and IDE extension
GitHub Copilot	Tool calls and tool results in Copilot CLI and VS Code Agent mode; prompts are audit-only	An HTTP MCP server for Copilot Chat

Agent platforms

Organization-managed AI services with centralized administration for users and integrations.

Platform	TrustGuard	TrustGate
Claude Enterprise	An inference hook evaluates model requests across the organization	An organization connector provides MCP tools in claude.ai, Desktop, Cowork, and Claude Code

AI gateways

Gateway integrations apply policy to model traffic that already passes through the gateway, without changes to each client application.

Input and output enforcement varies by gateway. Buffered responses can be evaluated before delivery when the adapter supports it. Streamed output may be monitor-only after delivery or unsupported, depending on the adapter. Direct provider calls bypass the gateway.

Gateway	Integration method
TrustGate	Native integration with no collector API key; covers LLM and MCP traffic; streamed output is monitor-only after delivery
Portkey	BYOG webhook for Portkey Cloud and self-hosted gateways
LiteLLM	Custom guardrail file loaded by the LiteLLM proxy
Kong	ai-custom-guardrail, on routes running AI Proxy
Apigee	A Shared Flow, per proxy or per environment
Azure APIM	send-request policies

Agent frameworks

These integrations connect at the agent, workflow, or tool boundary.

Framework	Integration method
LangChain	langchain-neuraltrust, an AgentMiddleware that hooks the agent loop and can stop a tool call before it executes
Strands Agents	strands-neuraltrust, lifecycle checks for prompts, history, responses, tool arguments, and results, with a complete checked-response interface
n8n	@neuraltrust/n8n-nodes-trustguard, a node whose verdict becomes a branch on the canvas
Microsoft Copilot Studio	An MCP tool pointed at a TrustGate consumer

Build your own

Use an SDK, middleware package, or the REST API for custom applications and unsupported platforms.

Integration	Package
Python SDK	trustguard-sdk
Node.js SDK	@neuraltrust/trustguard-sdk
REST	Any HTTP client, any language
Python middleware	FastAPI · Django · Flask
Node.js middleware	Express · Next.js
Go SDK	github.com/NeuralTrust/trustguard-sdk/go

Employee access to third-party AI

For employee access to AI services your organization does not operate, use the browser extension on managed Chrome and Edge. The extension is configured through managed browser policy rather than the collector catalog.

How TrustGuard integrations work

Most TrustGuard integrations call the evaluate API. TrustGate uses a native connection and does not require a collector API key.

POST {TRUSTGUARD_BASE_URL}/v1/evaluate
Authorization: Bearer <collector API key>
Content-Type: application/json

{
  "protocol": "llm",
  "direction": "input",
  "payload": { "input": "…" },
  "session_id": "sess-123",
  "consumer_id": "[e-mail]"
}

block → deny · ask → apply the host's approval behavior · transform → forward transformed_payload · else → forward

Set direction to "input" before the model call and "output" after it. TrustGate sets the direction automatically. See the Evaluate API for the full contract.

Create the API key from Agent Runtime → Collectors → Catalog in the console. The selected collector also provides setup instructions and a configuration snippet.

Create the policy in Observe mode. Observe records decisions in Activity without enforcing them. Review the results, then switch the policy to Enforce. See Policies.