# NeuralTrust | Platform for Agent Security.

## Docs

- [NeuralTrust Docs](https://neuraltrust-92b43583-develop.mintlify.site/index.md)
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/overview.md): Route, govern, and observe LLM and agent traffic with TrustGate, NeuralTrust's open-source AI gateway.
- [Architecture](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/architecture.md): TrustGate is one Go binary that boots one of three independent planes — Admin, Proxy, MCP — backed by Postgres and Redis. How a request flows end to end.
- [Quickstart](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/getting-started/quickstart.md): Create a TrustGate gateway, connect a provider, send a request, and inspect its trace from the NeuralTrust console.
- [Installation](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/getting-started/install.md): Choose a NeuralTrust-hosted SaaS data plane or deploy a Private TrustGate data plane in your environment.
- [Gateways](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/gateways.md): A gateway is the top-level tenant in TrustGate — created in the console, it owns the registries, consumers, auth, policies, and roles beneath it.
- [Registries](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/registries.md): A registry is an upstream backend — an LLM provider or an MCP server — connected from the console with credentials, options, and optional health checks.
- [Consumers](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/consumers.md): A consumer is the calling application's identity — create it in the console to set routing, credentials, and model policies, then copy Connect snippets for your apps.
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/auth.md): API keys, OAuth2, and OIDC — how clients authenticate as a consumer, and how to wire an IdP for Identity-based LLM routing and MCP login.
- [Okta](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/authorization/okta.md): End-to-end manual for wiring Okta to TrustGate: a custom authorization server, scopes, and a groups claim feeding OIDC role-based routing and OAuth2 for MCP.
- [Entra ID](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/authorization/entra-id.md): End-to-end manual for wiring Microsoft Entra ID (Azure AD) to TrustGate: an app registration with an exposed API scope and app roles feeding OIDC identity-based routing and OAuth2 for MCP.
- [Roles](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/concepts/roles.md): Roles power identity-based routing: an OIDC token's claims select a role in the console, and the role decides which registries, models, and MCP tools the caller may use.
- [Chat](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/chat.md): Use OpenAI, Anthropic, Cohere, or Gemini request formats while TrustGate selects and adapts the upstream provider.
- [Embeddings](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/embeddings.md): Call POST /{consumer}/v1/embeddings with an OpenAI-shaped body. TrustGate routes only to registries that can embed.
- [Images](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/images.md): Call POST /{consumer}/v1/images/generations (JSON) plus multipart /edits and /variations. TrustGate routes only to registries that can generate images.
- [Files](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/files.md): Call /{consumer}/v1/files to upload, list, retrieve, delete, and download content. TrustGate routes only to registries that expose a Files store.
- [Audio](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/audio.md): Call POST /{consumer}/v1/audio/speech (TTS, raw bytes) and /v1/audio/transcriptions (STT, multipart). TrustGate routes only to registries that can speak or transcribe.
- [Rerank](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/rerank.md): Call POST /{consumer}/v1/rerank with a Cohere v2 body. TrustGate routes only to registries that can rerank.
- [Models](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/endpoints/models.md): Call GET /{consumer}/v1/models to list the native model ids this consumer can actually call. This is gateway-owned discovery, not an upstream passthrough.
- [Smart routing](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/routing/smart-routing.md): Route each request by prompt complexity across Simple, Medium, and Hard tiers — pick cheaper models for easy prompts and stronger models for hard ones, configured on the consumer Routing tab.
- [Load balancing](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/routing/load-balancing.md): Distribute traffic across a consumer's registries from the console — smart routing, round-robin, weighted, least-connections, or random.
- [Model resolution](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/routing/model-resolution.md): How the model field in a client request selects a registry — including auto for load balancing and smart routing — and how to filter models on the consumer in the UI.
- [Fallback](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/routing/fallback.md): Retry across registries when an upstream fails — configure the ordered chain and triggers on the consumer Routing tab.
- [Policies](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/policies/overview.md): Configure rate limits, budgets, caching, tool governance, and guardrails globally or per consumer
- [Rate limiting & budgets](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/policies/rate-limiting.md): Limit request volume with Rate Limiter, and cap LLM spend over time with LLM Budget (token_rate_limiter) — tokens or dollars, aggregate or per-model.
- [Request size](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/policies/request-size.md): Reject oversized requests before they reach a provider with the request_size_limiter policy — by payload size and character count.
- [Prompt management](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/policies/prompt-model-controls.md): Prompt Template and Prompt Compression policies — inject system prompts or named versioned templates, and shrink request content before the model runs.
- [Tool governance](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/policies/tool-governance.md): Govern LLM function tools at the gateway — inject operator-authored tools, and rate-limit tool executions. Distinct from MCP toolkit grants on consumers and roles.
- [Guardrails](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/policies/guardrails.md): Inspect or rewrite prompts and responses inline at the gateway with TrustGuard, OpenAI Moderation, Azure Content Safety, AWS Bedrock, or Regex Replace policies.
- [MCP Gateway](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/mcp/overview.md): Aggregate Model Context Protocol servers behind one endpoint with toolkit scoping, upstream authentication, and OAuth2 for agents
- [OpenAPI to MCP](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/mcp/openapi.md): Generate MCP tools from an OpenAPI 3 document and connect them through TrustGate
- [Metrics worker](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/observability/metrics.md): How TrustGate records a per-request metrics event and ships it off the hot path through an asynchronous worker — no scraping, no request-path overhead.
- [Telemetry](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/observability/telemetry.md): TrustGate exports one OpenTelemetry log record per request — model, tokens, cost, latency breakdown, policy chain, and routing attempts — off the critical path.
- [Authentication](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/api/credentials.md): Authenticate to the TrustGate control-plane API with an admin JWT or a machine credential access token.
- [Build version](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/system/build-version.md): Returns build/version information for the running binary.
- [Liveness probe](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/system/liveness-probe.md): Reports whether the process is alive. Canonical path is /healthz; /health is an alias for load-balancer defaults.
- [Liveness probe](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/system/liveness-probe-1.md): Reports whether the process is alive. Canonical path is /healthz; /health is an alias for load-balancer defaults.
- [Readiness probe](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/system/readiness-probe.md): Reports whether the process is ready to serve traffic.
- [List config-sync data-plane connections](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/config-sync/list-config-sync-data-plane-connections.md): Returns the observed data-plane Sync connections, optionally filtered by opaque scope. Answers "is this data plane online?".
- [List gateways](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/gateways/list-gateways.md): Returns a paginated list of gateways.
- [Create a gateway](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/gateways/create-a-gateway.md): Creates a new gateway. Ownership tenant_id is required (JWT claim, or body for platform admins). The slug is optional: when omitted the server generates a unique random slug. If provided it must be a lowercase DNS label and unique. Platform JWT create requires stamped entitlements (tier + caps); ten…
- [Get a gateway](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/gateways/get-a-gateway.md): Returns a single gateway by id.
- [Update a gateway](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/gateways/update-a-gateway.md): Updates an existing gateway. Tenant JWTs may not send entitlements (422). Platform tier downgrades that would leave the tenant over the new MaxInstances return 409 — delete excess gateways first.
- [Delete a gateway](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/gateways/delete-a-gateway.md): Deletes a gateway and cascades the deletion to every resource that belongs to it (consumers, roles, policies, auths, registries and vault credentials).
- [List auths](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/auths/list-auths.md): Returns a paginated list of auths in a gateway.
- [Create an auth](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/auths/create-an-auth.md): Creates a new auth in a gateway.
- [Get an auth](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/auths/get-an-auth.md): Returns a single auth by id.
- [Update an auth](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/auths/update-an-auth.md): Updates an existing auth.
- [Delete an auth](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/auths/delete-an-auth.md): Deletes an auth from a gateway.
- [List consumers](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/list-consumers.md): Returns a paginated list of consumers in a gateway.
- [Create a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/create-a-consumer.md): Creates a new consumer in a gateway.
- [Get a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/get-a-consumer.md): Returns a single consumer by id.
- [Update a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/update-a-consumer.md): Updates an existing consumer. The optional `registries` field replaces the whole registry association set, so switching a role_based consumer to inline routing and attaching its registries happens in a single atomic request.
- [Delete a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/delete-a-consumer.md): Deletes a consumer from a gateway.
- [Attach an auth to a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/attach-an-auth-to-a-consumer.md): Associates an auth credential with a consumer (idempotent).
- [Detach an auth from a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/detach-an-auth-from-a-consumer.md): Removes the association between an auth credential and a consumer (idempotent).
- [Attach a policy to a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/attach-a-policy-to-a-consumer.md): Associates a policy with a consumer (idempotent). Editing the policy later affects every consumer it is attached to.
- [Detach a policy from a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/detach-a-policy-from-a-consumer.md): Removes the association between a policy and a consumer (idempotent).
- [Attach a registry to a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/attach-a-registry-to-a-consumer.md): Associates a registry with a consumer (idempotent). The optional body sets the registry weight for weighted load balancing.
- [Detach a registry from a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/detach-a-registry-from-a-consumer.md): Removes the association between a registry and a consumer (idempotent).
- [Attach a role to a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/attach-a-role-to-a-consumer.md): Associates a role with a role_based consumer (idempotent). Returns 409 for inline consumers.
- [Detach a role from a consumer](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/consumers/detach-a-role-from-a-consumer.md): Removes the association between a role and a consumer (idempotent).
- [List policies](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/list-policies.md): Returns a paginated list of policies in a gateway.
- [Create a policy](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/create-a-policy.md): Creates a new policy in a gateway.
- [Get a policy](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/get-a-policy.md): Returns a single policy by id.
- [Update a policy](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/update-a-policy.md): Updates an existing policy.
- [Delete a policy](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/delete-a-policy.md): Deletes a policy from a gateway.
- [Duplicate a policy](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/duplicate-a-policy.md): Creates a copy of an existing policy. The new policy reuses the plugin configuration (slug, settings, stages, enabled, priority, parallel) with a fresh id and an auto-generated name (suffix 2, 3, 4...). The copy has no consumer associations and is not global.
- [Mark a policy as global](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/mark-a-policy-as-global.md): Promotes a policy to gateway-wide scope (applies to every consumer).
- [Clear a policy's global scope](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/policies/clear-a-policys-global-scope.md): Demotes a global policy back to consumer-scoped (applies only to linked consumers).
- [List registries](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/list-registries.md): Returns one of two mutually exclusive variants: flat (items/page/size/total) when view and type are omitted, or grouped (view/groups/total_groups/total_instances) with view=grouped&type=LLM. Grouped requests require at most 200 total registries and must omit name, page, and size.
- [Create a backend](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/create-a-backend.md): Creates a new backend in a gateway.
- [Test a backend connection](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/test-a-backend-connection.md): Validates connectivity and credentials against the provider's API with a lightweight, auth-only request. Test either a stored registry (registry_id) or an inline candidate configuration (provider + auth). Always returns 200; inspect "ok" and "stage" for the outcome.
- [Get a backend](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/get-a-backend.md): Returns a single backend by id.
- [Update a backend](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/update-a-backend.md): Updates an existing registry.
- [Delete a backend](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/delete-a-backend.md): Deletes a backend from a gateway.
- [List an MCP backend's tools](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/registries/list-an-mcp-backends-tools.md): Introspects the MCP server behind the registry and returns its advertised tools. Each tool is passed through as the server declared it (name plus whatever else it exposes, e.g. description and inputSchema). Returns 502 when the upstream MCP server is unreachable.
- [List roles](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/list-roles.md): Returns a paginated list of roles in a gateway.
- [Create a role](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/create-a-role.md): Creates a new role in a gateway. model_policies cannot be set on create; bind registries first, then update the role.
- [Get a role](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/get-a-role.md): Returns a role by id within a gateway.
- [Update a role](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/update-a-role.md): Updates a role. model_policies may only reference registries already attached to the role.
- [Delete a role](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/delete-a-role.md): Deletes a role from a gateway.
- [Attach a registry to a role](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/attach-a-registry-to-a-role.md): Associates a registry with a role (idempotent).
- [Detach a registry from a role](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/roles/detach-a-registry-from-a-role.md): Removes the association between a registry and a role (idempotent).
- [List the MCP servers catalog](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/catalog/list-the-mcp-servers-catalog.md): Returns the curated catalog of well-known remote MCP servers, used to prefill MCP registry creation.
- [List model catalog](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/catalog/list-model-catalog.md): Returns the catalog of supported models, optionally filtered by provider. When gateway_id and registry_id are supplied for an AWS Bedrock registry, the list is narrowed to the models those credentials can invoke serverless (on-demand base models and system-defined inference profiles), excluding Bedr…
- [List policy catalog](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/catalog/list-policy-catalog.md): Returns the catalog of available policies grouped by type. Each entry includes the settings schema needed to render its configuration form dynamically.
- [List provider catalog](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/catalog/list-provider-catalog.md): Returns the catalog of supported LLM providers.
- [Get a playground trace](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/playground/get-a-playground-trace.md): Returns the metrics Event captured for a playground request, keyed by the X-AG-Trace-Id returned in the proxy response. Traces expire after a short TTL.
- [Proxy chat completion](https://neuraltrust-92b43583-develop.mintlify.site/api-reference/proxy/proxy-chat-completion.md): Forwards an OpenAI Chat Completions request to the selected provider. Proxy plane route: /{consumer_slug}/v1/chat/completions. Other fixed routes include /v1/messages (Anthropic) and /v1/responses (OpenAI Responses). Inline consumers may authenticate with an api key via X-AG-API-Key, x-api-key, or A…
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/overview.md): Learn how TrustGuard AI guardrails inspect LLM and agent traffic, apply security policies, and return verdicts for collectors to enforce.
- [How it works](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/how-it-works.md): How TrustGuard policy actions are enforced across collectors, including monitoring, blocking, redaction, and approval support
- [Detectors](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/concepts/detectors.md): Configure reusable detector instances and attach them to TrustGuard policies
- [Policies](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/concepts/policies.md): A policy is where enforcement lives: gates that match request attributes before detection, detector rules that run detectors and decide the action, and a policy-wide Observe/Enforce switch.
- [Collectors](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/concepts/collectors.md): How TrustGuard collectors receive traffic, authenticate requests, select policies, and attribute activity
- [Data handling](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/data-handling.md): What TrustGuard stores when it evaluates a request, which values are redacted before storage, and how long records are retained.
- [Detector catalog](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/detectors/overview.md): The built-in TrustGuard detector catalog across data loss prevention, content security, and agent/MCP security.
- [Data loss prevention](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/detectors/data-loss-prevention.md): Detect and mask PII and secrets in AI traffic on input and output. Configure data categories and custom rules in the console — the only transform-capable detector.
- [Content security detectors](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/detectors/content-security.md): Jailbreak detection, toxicity, Moderation, and document/URL screening for indirect prompt injection and PII.
- [Agent & MCP security detectors](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/detectors/agent-mcp-security.md): Indirect prompt injection detection for MCP tool results and other tool-sourced content.
- [Evaluate API](https://neuraltrust-92b43583-develop.mintlify.site/trustguard/api/evaluate.md): Request, evaluation pipeline, and response reference for POST /v1/evaluate, including authentication, attachments, and status codes
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/overview.md): Run repeatable AI red teaming and functional evaluations against models, agents, and LLM endpoints with TrustTest.
- [Installation](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/installation.md)
- [Quickstart](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/quickstart.md)
- [Quickstart with Local LLM](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/local-llm.md)
- [Http Target](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/http-model.md)
- [Run Basic Red Teaming](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/basic-red-teaming.md)
- [LLM as a Judge](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/llm-as-judge.md)
- [Test generation with Prompt](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/prompt-dataset.md)
- [Test generation with RAG](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/rag.md)
- [Multi-turn Crescendo red teaming](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/iterate.md)
- [Run Responsibility Evaluation](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/compliance.md)
- [Save and load Scenarios](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/client.md)
- [Custom LLM as a Judge](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/getting-started/tutorials/custom-llm-judge.md)
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/core-concepts/overview.md)
- [Test Generation](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/core-concepts/test-cases.md)
- [Evaluation](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/core-concepts/evaluation-scenarios.md)
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/connect/overview.md)
- [Custom Targets](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/connect/custom.md)
- [HTTP Target](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/connect/http.md)
- [LLMs & Embeddings](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/connect/llms.md)
- [Connect to NeuralTrust](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/connect/client.md)
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/overview.md): Complete reference of all TrustTest attack probes and techniques
- [Content Bias](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/content-bias.md)
- [Sensitive Data Leak](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/sensitive-data-leak.md)
- [System Prompt Disclosure](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/system-prompt-disclosure.md)
- [Input Leakage](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/input-leakage.md)
- [Unsafe Outputs](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/unsafe-outputs.md)
- [Off-Topics](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/off-topic.md)
- [Agentic Behavior](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/agentic-behavior.md)
- [Prompt Injections Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/overview.md): Complete catalog of prompt injection attack techniques in TrustTest
- [Single Turn Attacks](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/single-turn/overview.md): All 39 single-turn prompt injection probes and how to run them
- [Multi-Turn Attacks](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/multi-turn/overview.md): Sophisticated attacks across multiple conversation turns
- [Crescendo Attack](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/multi-turn/crescendo.md): Test resistance to gradual escalation attacks across multiple turns
- [Echo Chamber Attack](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/multi-turn/echo-chamber.md): Test resistance to reinforcement-based manipulation through positive feedback
- [Multi-Turn Manipulation](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/multi-turn/multi-turn-manipulation.md): Test resistance to gradual conditioning across multiple conversation turns
- [Payload Splitting](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/multi-turn/payload-splitting.md): Split a malicious instruction across conversation turns
- [From Dataset](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/threat-detection/prompt-injections/from-dataset.md): Load prompt injection attacks from curated or custom datasets
- [Creating Custom Probes](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/creating-custom-probes.md): Developer guide for building custom attack probes in TrustTest
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/functional/overview.md): Evaluate your AI model's functional correctness and quality
- [From RAG](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/functional/from-rag.md): Generate functional tests from your Retrieval-Augmented Generation knowledge base
- [From Dataset](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/functional/from-dataset.md): Create functional tests from existing question-answer datasets
- [From Prompt](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/functional/from-prompt.md): Generate functional tests dynamically using LLM-powered prompt generation
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/knowledge-base/overview.md): Knowledge base connectors used to generate RAG and functional tests
- [Test Generation](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/automatic-test-generation.md)
- [In-memory](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/knowledge-base/connectors/in-memory.md): Local document store for prototyping RAG tests
- [Azure AI Search](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/knowledge-base/connectors/azure.md): Connect Azure AI Search as a TrustTest knowledge base
- [Neo4j](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/knowledge-base/connectors/neo4j.md): Connect a Neo4j graph store as a TrustTest knowledge base
- [PostgreSQL + pgvector](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/knowledge-base/connectors/postgres.md): Connect a PostgreSQL pgvector store as a TrustTest knowledge base
- [Upstash](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/create/knowledge-base/connectors/upstash.md): Connect Upstash Vector as a TrustTest knowledge base
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/overview.md)
- [Evaluation Context](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/evaluation-strategy.md)
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/overview.md)
- [Completeness](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/completeness.md)
- [Correctness](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/correctness.md)
- [Tone](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/tone.md)
- [True/False](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/true-false.md)
- [URL Correctness](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/url-correctness.md)
- [RAG Poisoning](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/rag-poisoning.md)
- [Answer Relevance](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/answer-relevance.md): Score how relevant a response is to the question
- [Custom](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/llm-as-a-judge/custom.md): Build a custom LLM judge with CustomEvaluatorExpected or CustomEvaluatorObjective
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/overview.md)
- [BLEU](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/bleu.md)
- [Equals](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/equals.md)
- [Language](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/language.md)
- [Regex](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/regex.md)
- [Signature evaluators](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/signature.md): Detect Virus, Spam, Phishing, and XSS test signatures in model output
- [Bias comparison](https://neuraltrust-92b43583-develop.mintlify.site/trusttest/evaluate-result/heuristics/bias-comparison.md): Compare paired answers for consistency with BiasComparisonEvaluator
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/integrations/overview.md): Connect NeuralTrust to coding agents, agent platforms, AI gateways, agent frameworks, and applications
- [Claude Code](https://neuraltrust-92b43583-develop.mintlify.site/integrations/claude-code.md): Evaluate Claude Code prompts, commands, and tool results with TrustGuard, and connect the CLI to TrustGate over MCP
- [Cursor](https://neuraltrust-92b43583-develop.mintlify.site/integrations/cursor.md): Configure TrustGuard firewall hooks for Cursor and connect the Cursor agent to TrustGate over MCP
- [Codex](https://neuraltrust-92b43583-develop.mintlify.site/integrations/codex.md): Configure TrustGuard lifecycle hooks for OpenAI Codex and connect Codex to TrustGate over MCP
- [GitHub Copilot](https://neuraltrust-92b43583-develop.mintlify.site/integrations/github-copilot.md): Configure TrustGuard hooks for GitHub Copilot agent surfaces and connect Copilot Chat to TrustGate over MCP
- [Claude Enterprise](https://neuraltrust-92b43583-develop.mintlify.site/integrations/claude-enterprise.md): Configure organization-wide Claude inference hooks with TrustGuard and managed MCP connectors with TrustGate
- [TrustGate](https://neuraltrust-92b43583-develop.mintlify.site/integrations/trustgate.md): Configure TrustGuard in TrustGate for LLM and MCP traffic, including policy scope, verdict handling, and failure behavior
- [Portkey](https://neuraltrust-92b43583-develop.mintlify.site/integrations/portkey.md): Evaluate Portkey requests and responses through a TrustGuard BYOG webhook
- [LiteLLM](https://neuraltrust-92b43583-develop.mintlify.site/integrations/litellm.md): Connect LiteLLM to TrustGuard with a custom guardrail file that evaluates proxy requests and responses
- [Kong](https://neuraltrust-92b43583-develop.mintlify.site/integrations/kong.md): Evaluate prompts and completions on Kong AI Proxy routes
- [Apigee](https://neuraltrust-92b43583-develop.mintlify.site/integrations/apigee.md): Evaluate prompts and completions in an Apigee Shared Flow
- [Azure API Management](https://neuraltrust-92b43583-develop.mintlify.site/integrations/azure-apim.md): Evaluate prompts and completions in the Azure API Management policy chain
- [LangChain](https://neuraltrust-92b43583-develop.mintlify.site/integrations/langchain.md): Add TrustGuard middleware to LangChain agents, configure evaluation hooks, handle verdicts, and verify enforcement
- [Strands Agents](https://neuraltrust-92b43583-develop.mintlify.site/integrations/strands.md): Add TrustGuard to Strands Agents, configure input and output checks, protect tool calls, and handle policy decisions
- [n8n](https://neuraltrust-92b43583-develop.mintlify.site/integrations/n8n.md): Use the TrustGuard community node in n8n to evaluate prompts and model responses and route workflow items by verdict
- [Microsoft Copilot Studio](https://neuraltrust-92b43583-develop.mintlify.site/integrations/copilot-studio.md): Connect Microsoft Copilot Studio agents to TrustGate over MCP using OAuth and dynamic client registration
- [Python SDK](https://neuraltrust-92b43583-develop.mintlify.site/integrations/python-sdk.md): Use the TrustGuard SDK in Python to evaluate model input and output and enforce verdicts in your application
- [Node.js SDK](https://neuraltrust-92b43583-develop.mintlify.site/integrations/node-sdk.md): Use the TrustGuard SDK in JavaScript and TypeScript to evaluate model input and output and enforce verdicts in your application
- [REST API](https://neuraltrust-92b43583-develop.mintlify.site/integrations/rest.md): Call the TrustGuard evaluation API from any HTTP client and handle verdicts, retries, and failures in your application
- [Python middleware](https://neuraltrust-92b43583-develop.mintlify.site/integrations/python-middleware.md): Use TrustGuard middleware with FastAPI, Django, and Flask to evaluate request and response payloads on selected routes
- [Node.js middleware](https://neuraltrust-92b43583-develop.mintlify.site/integrations/node-middleware.md): Use TrustGuard middleware with Express and Next.js to evaluate request and response payloads on selected routes
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/platform/overview.md): Platform Settings is where you manage your NeuralTrust organization — identity, users and roles, SSO, integrations, and workspace configuration.
- [Organization settings](https://neuraltrust-92b43583-develop.mintlify.site/platform/general.md): Everything in Platform → Workspace → General: organization name, organization ID, leave organization, and delete organization — plus how org settings relate to users, SSO, and integrations.
- [User & Roles](https://neuraltrust-92b43583-develop.mintlify.site/platform/users.md): Manage who belongs to your NeuralTrust organization — users, invitations, platform roles, and per-product permission levels.
- [Microsoft Entra ID SSO](https://neuraltrust-92b43583-develop.mintlify.site/platform/sso.md): Step-by-step guide to configure Microsoft Entra ID (Azure AD) Single Sign-On for NeuralTrust. Enable corporate authentication for your organization.
- [Google Workspace SSO](https://neuraltrust-92b43583-develop.mintlify.site/platform/google-workspace-sso.md): Step-by-step guide to configure Google Workspace Single Sign-On for NeuralTrust, including optional directory group sync via a service account.
- [Generic OIDC SSO](https://neuraltrust-92b43583-develop.mintlify.site/platform/generic-oidc-sso.md): Configure Single Sign-On with any OpenID Connect compliant identity provider including Okta, Auth0, Google Workspace, and more.
- [Break the Glass](https://neuraltrust-92b43583-develop.mintlify.site/platform/break-glass.md): Configure up to five emergency Break the Glass accounts in User & Roles. A single-organization account signs in with password only.
- [Role Provisioning](https://neuraltrust-92b43583-develop.mintlify.site/platform/role-provisioning.md): Map identity provider groups to NeuralTrust platform roles, set a default role, and choose when provisioning applies. One place for group-to-role mapping across Entra ID and Google Workspace.
- [SCIM Provisioning](https://neuraltrust-92b43583-develop.mintlify.site/platform/scim.md): Set up SCIM automatic user provisioning with Microsoft Entra ID. Automatically sync users between Azure AD and NeuralTrust.
- [Manual User Sync](https://neuraltrust-92b43583-develop.mintlify.site/platform/user-sync.md): Provision users from Microsoft Entra ID groups without SCIM, using group-to-role mapping in Role Provisioning.
- [Alerts](https://neuraltrust-92b43583-develop.mintlify.site/platform/alerts.md): Turn TrustGuard and TrustGate telemetry into prioritized, deduplicated alerts. Enable predefined detection use cases, author custom rules, correlate across products, and forward findings to your SIEM.
- [Use Cases](https://neuraltrust-92b43583-develop.mintlify.site/platform/use-cases.md): Author custom detection rules over TrustGuard and TrustGate telemetry. Configure scope, AND/OR conditions, time windows, severity, and assignees — with a live rule preview compiled to the AlertEngine DSL.
- [Event Schema](https://neuraltrust-92b43583-develop.mintlify.site/platform/event-schema.md): Schema reference for TrustGuard and TrustGate metadata events — the fields AlertEngine rules match on, how detection normalization works, and what is not stored.
- [Integrations](https://neuraltrust-92b43583-develop.mintlify.site/platform/alert-integrations.md): Forward NeuralTrust alert findings to your SIEM. Connect Microsoft Sentinel, Datadog, Splunk, Elastic, IBM QRadar, or a generic webhook and stream each new alert as an OCSF Detection Finding.
- [Audit Logs](https://neuraltrust-92b43583-develop.mintlify.site/platform/audit-logs.md): Browse platform audit events in Telemetry → Logs. Track authentication, user and role changes, SSO, and product configuration — with filters, search, CSV export, and SOC2 retention.
- [Security posture](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/security/overview.md): NeuralTrust's platform-wide security model — authentication, access control, networking, encryption, and compliance guarantees.
- [Data privacy](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/data-privacy/overview.md): Data sovereignty, GDPR / HIPAA / SOX compliance, and the privacy-by-design architecture that keeps sensitive AI data inside your environment.
- [Browser extension](https://neuraltrust-92b43583-develop.mintlify.site/platform/browser-extension.md): Deploy Discover by NeuralTrust to monitor and control employee use of third-party AI services in managed browsers
- [Custom domain](https://neuraltrust-92b43583-develop.mintlify.site/platform/custom-domain.md): Configure the NeuralTrust application hostname and distinguish it from runtime ingress domains.
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/overview.md): Compare SaaS, Hybrid, External, and Central control plane deployment models.
- [Hybrid](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/hybrid.md): Run the request path in your cluster with the control plane on NeuralTrust SaaS — architecture, network, install, and high availability.
- [External (self-hosted)](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/external.md): Run the full NeuralTrust platform — control plane, data plane, and analytics — inside your own cluster.
- [Central control plane](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/central.md): Run your own control plane for NeuralTrust data planes spread across several clusters.
- [Requirements and dependencies](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/architecture.md): What you have to provide, the ports between components, and how much cluster capacity to plan for.
- [Configuration](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/configuration.md): Every chart switch that changes a deployment — products, datastores, ingress, Firewall workers, and cross-cluster endpoints.
- [Container images](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/images.md): Pull NeuralTrust images directly with the key we send you, or mirror them into your own registry.
- [Secrets](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/secrets.md): Handle credentials generated for a private TrustGate gateway.
- [Console setup](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/console-setup.md): Before installing, create TrustGate and TrustGuard in the console and collect the tokens the Hybrid data plane needs.
- [Config sync](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/config-sync.md): How a data plane gets its configuration, what it caches, and how it behaves when the control plane is unreachable.
- [Validation checklist](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/validation.md): What to prove before a NeuralTrust install counts as done — the checks that pods being Ready does not cover.
- [Cloud notes](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/cloud-notes.md): Provider particularities for EKS, AKS, GKE, and conformant Kubernetes — cluster creation, ingress, certificates, and managed stores.
- [OpenShift](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/openshift/overview.md): OpenShift prerequisites, Routes, and SecurityContextConstraints for the NeuralTrust chart.
- [Troubleshooting](https://neuraltrust-92b43583-develop.mintlify.site/neuraltrust/deployment/troubleshooting.md): Symptoms you will actually see, and what causes them.
- [Gap trusttest docs](https://neuraltrust-92b43583-develop.mintlify.site/gap-trusttest-docs.md)
- [Claude integrations](https://neuraltrust-92b43583-develop.mintlify.site/integrations/claude.md): Find the Claude Code and Claude Enterprise setup guides for TrustGuard and TrustGate
- [Support](https://neuraltrust-92b43583-develop.mintlify.site/support.md): Report bugs and issues, ask the community, or check service status.
- [Alerts](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/alerts.md): Rule-based alerts that notify your team when an AI resource crosses a risk threshold — so posture regressions never sit unnoticed.
- [Data handling](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/data-handling.md): What TrustLens collects, what it never collects, where it stores data, and how to revoke access.
- [How it works](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/how-it-works.md): The five stages of the TrustLens lifecycle — connect, discover, assess, monitor, and alert — and how data flows from your environment into a single AI inventory.
- [Azure](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/integrations/azure.md): Azure AI Foundry (v2), AI Hub (classic Foundry), Azure OpenAI Classic (v1), and legacy ML Workspaces — all under one integration.
- [Endpoint Discovery (MDM)](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/integrations/endpoint-mdm.md): Deploy a read-only Device Discovery script via Microsoft Intune or Kandji to inventory AI tools — IDEs, browsers, extensions, agent CLIs, MCP servers, and agent configs — across macOS and Windows endpoints.
- [GCP Vertex AI](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/integrations/gcp-vertex-ai.md): Discover and monitor Vertex AI Reasoning Engines, models, datasets, and Model Armor guardrails across your Google Cloud project.
- [GitHub](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/integrations/github.md): Discover agent configs, MCP server definitions, and agent source code across your GitHub organization using a read-only GitHub App.
- [M365 Copilot & Copilot Studio](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/integrations/m365-copilot.md): Discover Copilot Studio bots via Dataverse and Microsoft 365 Copilot agents via the Microsoft Graph Agent Registry.
- [Mistral AI](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/integrations/mistral.md): Discover and monitor Mistral agents, models, files, document libraries, and native moderation guardrails using a single API key.
- [Inventory](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/inventory.md): The unified catalog of every AI surface across your organization — agents, models, datasets, IDEs, browsers, extensions, agent CLIs, MCP servers, agent configs, and managed endpoints.
- [Overview](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/overview.md): Discover and continuously assess every AI surface across your organization — agents, models, IDEs, browsers, MCP servers, and managed endpoints — from a single inventory.
- [Risk & findings](https://neuraltrust-92b43583-develop.mintlify.site/trustlens/risk-and-findings.md): How TrustLens scores posture — the security controls evaluated per resource type, their weights, and how individual control results roll up to a 0–100 score and a risk level.
- [Trusttest sample code](https://neuraltrust-92b43583-develop.mintlify.site/trusttest-sample-code.md)

## OpenAPI Specs

- [openapi](https://neuraltrust-92b43583-develop.mintlify.site/trustgate/api/openapi.json)

## Optional

- [Blog](https://neuraltrust.ai/blog)
- [Github](https://github.com/NeuralTrust)
- [Community](https://neuraltrustcommunity.slack.com/join/shared_invite/zt-2xl47cag6-_HFNpltIULnA3wh4R6AqBg)