# TrojAI

**Canonical:** https://apis.io/providers/trojai/  
**Website:** https://troj.ai/  
**APIs profiled:** 1

TrojAI is an enterprise AI security platform (acquired by A10 Networks) that lets organizations deploy AI models and agents safely. Its two products — TrojAI Detect (generative-AI red teaming, model robustness stress-testing, and integrity/risk audits for tabular and NLP models) and TrojAI Defend (a runtime firewall / proxy that inspects prompts and tool calls for prompt injection, jailbreaks, data leakage, toxic content, and rogue MCP/tool abuse) — are managed through a self-hosted RESTful platform API (/api/v2, authenticated with the x-trojai-api-key header), a Firewall Proxy API, a Python SDK (trojai-sdk), and a Keycloak-backed web application. It deploys as Cloud or Enterprise (Helm/Kubernetes).

## Kin Score — 37.3 / 100 (thin)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 37.3).

| Facet | Score |
|---|---|
| Discoverability | 75.9 |
| Contract Quality | 28.2 |
| Governance | 18.2 |
| Contract Governance | 18.2 |
| Operational Transparency | 26.3 |
| Developer Ergonomics | 64.3 |
| Commercial Clarity | 21.1 |
| Access Clarity | 21.1 |

## Agent readiness — 23.9 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (1)

- **TrojAI Platform API** — RESTful JSON API to manage the TrojAI platform programmatically (users, groups, roles/permissions, datasets, models, firewall policies/configs, firewall events, red team jobs an...

## Security (3)

- **Trojai Authentication** — apiKey · 2 schemes
- **Trojai Domain Security** — TLSv1.3 · DNSSEC · DMARC
- **Trojai Vulnerability Disclosure** — Hackerone · contact published

## Tags

Company, AI Security, Machine-Learning, LLM Security, Red Teaming, AI Firewall, Prompt Injection, Model Risk, MLOps, Agentic AI

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/trojai/). Scores are computed from the provider's own public artifacts under a published rubric.