TrojAI

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).

TrojAI publishes 1 API on the APIs.io network: Platform API. Tagged areas include Company, AI Security, Machine Learning, LLM Security, and Red Teaming.

TrojAI’s developer surface includes documentation, API reference, getting-started guide, engineering blog, support, authentication, changelog, and 13 more developer resources.

38.1/100 thin ▬ flat Agent 27/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
1 APIs
CompanyAI SecurityMachine LearningLLM SecurityRed TeamingAI FirewallPrompt InjectionModel RiskMLOpsAgentic AI

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 38.1/100 · thin
Contract Quality 9.4 / 25
Developer Ergonomics 11.7 / 20
Commercial Clarity 4.2 / 20
Operational Transparency 3.4 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 27/100 · agent aware
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 15
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/trojai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

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 Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Trojai Authentication

apiKey · 2 schemes

SECURITY

Trojai Domain Security

TLSv1.3 · DNSSEC · DMARC

SECURITY

Trojai Vulnerability Disclosure

Hackerone · contact published

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 3

Pagination, idempotency, versioning, errors, and events

Build 2

SDKs, sample code, and the tooling you integrate with

Access & Security 4

Authentication, authorization, and security posture

Operate 2

Status, limits, changes, and where to get help

Commercial 2

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: trojai
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/trojai.png
name: TrojAI
description: 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).
url: https://raw.githubusercontent.com/api-evangelist/trojai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- techstars
x-tier: profiled
x-tier-reason: enriched-real-api-surface
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- AI Security
- Machine Learning
- LLM Security
- Red Teaming
- AI Firewall
- Prompt Injection
- Model Risk
- MLOps
- Agentic AI
apis:
- name: TrojAI Platform API
  description: RESTful JSON API to manage the TrojAI platform programmatically (users, groups, roles/permissions, datasets,
    models, firewall policies/configs, firewall events, red team jobs and results, and secrets) — designed to be driven from
    an MLOps or CI/CD pipeline. Authenticated with an API key in the x-trojai-api-key header. The platform is self-hosted
    (Cloud or Enterprise), so the host is per-deployment and a per-tenant Swagger UI is served at https://<your_trojai_host>/docs.
  humanURL: https://docs.troj.ai/reference/eng-api
  baseURL: https://your-trojai-host.example/api/v2
  x-base-url-note: Host is per-tenant (self-hosted Cloud/Enterprise). The documented base path is /api/v2 on the deployment
    host (https://<your_trojai_host>); there is no single public production host.
  properties:
  - type: APIReference
    url: https://docs.troj.ai/reference/eng-api
  - type: Documentation
    url: https://docs.troj.ai/
  - type: Authentication
    url: authentication/trojai-authentication.yml
  - type: Swagger
    url: https://docs.troj.ai/reference/eng-api
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://troj.ai/
- type: DeveloperPortal
  url: https://docs.troj.ai/
- type: Documentation
  url: https://docs.troj.ai/
- type: APIReference
  url: https://docs.troj.ai/reference/eng-api
- type: GettingStarted
  url: https://docs.troj.ai/trojai/getting-started/for-data-scientists
- type: Blog
  url: https://troj.ai/blog/
- type: Support
  url: https://troj.ai/company/contact/
- type: PrivacyPolicy
  url: https://troj.ai/legal/privacy-policy/
- type: TermsOfService
  url: https://troj.ai/legal/terms-of-service/
- type: Security
  url: https://troj.ai/legal/security/
- type: LLMsTxt
  url: llms/trojai-llms.txt
- type: Authentication
  url: authentication/trojai-authentication.yml
- type: Packages
  url: packages/trojai-packages.yml
- type: SDKs
  url: packages/trojai-packages.yml
- type: ChangeLog
  url: changelog/trojai-changelog.yml
- type: Lifecycle
  url: lifecycle/trojai-lifecycle.yml
- type: Conventions
  url: conventions/trojai-conventions.yml
- type: Conformance
  url: conformance/trojai-conformance.yml
- type: DomainSecurity
  url: security/trojai-domain-security.yml
- type: VulnerabilityDisclosure
  url: security/trojai-vulnerability-disclosure.yml
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 10
  pass: local-v1