ActiveFence

ActiveFence — now operating as Alice — is an AI security, safety and trust & safety company headquartered in New York and Tel Aviv. It sells two product families through one REST API at api.alice.io: ActiveFamily (ActiveScore automated detection plus the ActiveOS moderation workbench) for user-generated-content trust and safety across text, image, video and audio in 120+ languages and 20+ abuse areas; and WonderSuite for generative-AI protection — WonderBuild (pre-deployment red teaming and adversarial assessment of models, apps and agents), WonderFence (real-time runtime guardrails that evaluate prompts and responses for prompt injection, jailbreaks, PII leakage and policy violations) and WonderCheck (ongoing post-launch evaluation and drift detection). The API offers synchronous endpoints for low-latency moderation and asynchronous endpoints that acknowledge receipt and post results back to a customer-configured callback URL, plus configurable action webhooks fired from the ActiveOS moderation view or an automated workflow. Authentication is a single af-api-key header issued from the platform console; the default rate limit is 50 requests per second. First-party SDKs ship for Python (wonderfence-sdk) and TypeScript (@alice-io/wonderfence-ts-sdk), with a Parlant integration and the open-source Caterpillar agent-skill security scanner. Alice is SOC 2 and ISO 27001 certified.

ActiveFence publishes 7 APIs on the APIs.io network, including api keys API, Collection API, Content API, and 4 more. Tagged areas include ai-safety, ai-security, trust-and-safety, content-moderation, and guardrails.

The ActiveFence catalog on APIs.io includes 1 event-driven AsyncAPI specification.

ActiveFence’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, CLI, authentication, and 23 more developer resources.

🌐 Visit website 📡 Source on GitHub

54.7/100 developing ▬ flat Agent 50/100 agent ready Full breakdown ↓
scored 2026-08-17 · rubric v0.11.0

7 APIs 1 MCP Servers

ai-safetyai-securitytrust-and-safetycontent-moderationguardrailsred-teamingllm-securityprompt-injectionai-governancerisk-scoringuser-generated-contentchild-safety

Kin Score

Kin Score How this is scored →
scored 2026-08-17 · rubric v0.11.0

Composite quality — 54.7/100 · developing

Contract Quality 18.1 / 25

Developer Ergonomics 14.7 / 20

Commercial Clarity 8.4 / 20

Operational Transparency 1.7 / 13

Governance 2.5 / 12

Discoverability 9.3 / 10

Agent readiness — 50/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

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/activefence: 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 7

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

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

Login

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

MCPServer

AgenticAccess

LLMsTxt

WellKnown

AgentSkill

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Lifecycle

Conformance

Webhooks

DataModel

Build 5

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Postman

Packages

SDKs

CLI

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

Compliance

Compliance

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support

Support

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: activefence
name: ActiveFence
description: 'ActiveFence — now operating as Alice — is an AI security, safety and trust & safety company headquartered in
  New York and Tel Aviv. It sells two product families through one REST API at api.alice.io: ActiveFamily (ActiveScore automated
  detection plus the ActiveOS moderation workbench) for user-generated-content trust and safety across text, image, video
  and audio in 120+ languages and 20+ abuse areas; and WonderSuite for generative-AI protection — WonderBuild (pre-deployment
  red teaming and adversarial assessment of models, apps and agents), WonderFence (real-time runtime guardrails that evaluate
  prompts and responses for prompt injection, jailbreaks, PII leakage and policy violations) and WonderCheck (ongoing post-launch
  evaluation and drift detection). The API offers synchronous endpoints for low-latency moderation and asynchronous endpoints
  that acknowledge receipt and post results back to a customer-configured callback URL, plus configurable action webhooks
  fired from the ActiveOS moderation view or an automated workflow. Authentication is a single af-api-key header issued from
  the platform console; the default rate limit is 50 requests per second. First-party SDKs ship for Python (wonderfence-sdk)
  and TypeScript (@alice-io/wonderfence-ts-sdk), with a Parlant integration and the open-source Caterpillar agent-skill security
  scanner. Alice is SOC 2 and ISO 27001 certified.'
image: https://cdn.prod.website-files.com/69005ca0f0832195cbc1370c/6966208e49b12596bab0f42e_Group%201707480796.png
url: https://raw.githubusercontent.com/api-evangelist/activefence/refs/heads/main/apis.yml
x-type: company
x-source: harvest:secondary-market
x-enrichment:
  date: '2026-08-06'
  status: enriched
  artifacts_added: 16
  pass: local-v1
specificationVersion: '0.21'
created: '2026-08-06'
modified: '2026-08-06'
tags:
- ai-safety
- ai-security
- trust-and-safety
- content-moderation
- guardrails
- red-teaming
- llm-security
- prompt-injection
- ai-governance
- risk-scoring
- user-generated-content
- child-safety
apis:
- aid: activefence:activefence-api-keys-api
  name: ActiveFence api keys API
  description: Provides APIs to manage API key(s), including adding new keys, listing existing keys, and deleting keys.
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - api keys
  properties:
  - type: OpenAPI
    url: openapi/activefence-api-keys-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
- aid: activefence:activefence-collection-api
  name: ActiveFence Collection API
  description: Collection API Represents grouped entities. A collection is comprised of multiple items grouped together in
    a playlist, album, folder, group or channel on your platform. For example, a playlist of videos (holding a list of videos),
    a discussion group (holding a list of posts), a folder (holding a list of files) or a channel.
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - collection
  properties:
  - type: OpenAPI
    url: openapi/activefence-collection-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
- aid: activefence:activefence-content-api
  name: ActiveFence Content API
  description: Content APIs Represents WHAT content was created on your platform, such as a post, comment, review, message,
    article or data. For example, a web page containing a video, a customer review of a product, a comment and so on.
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - content
  properties:
  - type: OpenAPI
    url: openapi/activefence-content-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
- aid: activefence:activefence-flags-api
  name: ActiveFence Flags API
  description: The Flags API enables you to send details about the flag made on an item on your platform to the Alice T&S
    platform.
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - flags
  properties:
  - type: OpenAPI
    url: openapi/activefence-flags-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
- aid: activefence:activefence-users-api
  name: ActiveFence Users API
  description: Users API Represents WHO created content on your platform. These are the end users that have uploaded content
    to your platform, meaning the people who are the creators or publishers of the content. For example, the account used
    for creating an image. A user can also be someone who likes, reacts, follows, administers, shares items and so on.
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - users
  properties:
  - type: OpenAPI
    url: openapi/activefence-users-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
- aid: activefence:activefence-wonderbuild-api
  name: ActiveFence Wonder Build API
  description: WonderBuild provides red teaming and security assessment tools for AI applications. APIs for running comprehensive
    security assessments on gen-AI applications.
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - WonderBuild
  properties:
  - type: OpenAPI
    url: openapi/activefence-wonderbuild-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
- aid: activefence:activefence-wonderfence-api
  name: ActiveFence Wonder Fence API
  description: "WonderFence provides real-time guardrails for AI-generated content. APIs for evaluating and moderating AI-generated\
    \ content and interactions to protect against harmful outputs and prompt attacks.\n\n## API Response Key Mapping\nThe\
    \ following table is a mapping between violation types, their categories, and their corresponding API response keys:\n\
    \nViolation Type | Category | API Response Key\n---------------|----------|----------------\n Impersonation | Security\
    \ | prompt_attack.impersonation\n System Prompt Override | Security | prompt_attack.system_prompt_override\n Encoding\
    \ | Security | prompt_injection.general_encoding\n Prompt Injection | Security | prompt_injection.general\n PII | Privacy\
    \ | privacy_violation.PII\n Harassment or Bullying | Safety | abusive_or_harmful.harassment_or_bullying\n Profanity |\
    \ Safety | abusive_or_harmful.profanity\n Hate Speech | Safety | abusive_or_harmful.hate_speech\n Child Abuse | Safety\
    \ | abusive_or_harmful.child_abuse\n Suicide and Self-harm | Safety | self_harm.general\n Adult Content | Safety | adult_content.general\n\
    \ Weapons | Safety | unauthorised_sales.weapons\n Legal Advice | Safety | deny_topics.legal_advice\n Financial Advice\
    \ | Safety | deny_topics.financial_advice"
  humanURL: https://docs.activefence.com/index.html
  baseURL: https://api.alice.io
  tags:
  - WonderFence
  properties:
  - type: OpenAPI
    url: openapi/activefence-wonderfence-api-openapi.yml
  - type: Documentation
    url: https://docs.activefence.com/index.html
  - type: APIReference
    url: https://docs.activefence.com/index.html
  - type: Authentication
    url: authentication/activefence-authentication.yml
  - type: Conventions
    url: conventions/activefence-conventions.yml
  - type: ErrorCatalog
    url: errors/activefence-problem-types.yml
  - type: DataModel
    url: data-model/activefence-data-model.yml
  - type: Webhooks
    url: asyncapi/activefence-webhooks.yml
  - type: Postman
    url: https://www.postman.com/activefence-demo-team
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: MCPServer
  url: mcp/activefence-mcp.yml
- type: AgenticAccess
  url: agentic-access/activefence-agentic-access.yml
- type: Website
  url: https://alice.io/
- type: DeveloperPortal
  url: https://docs.activefence.com/index.html
- type: Documentation
  url: https://docs.activefence.com/index.html
- type: APIReference
  url: https://docs.activefence.com/index.html
- type: GettingStarted
  url: https://docs.activefence.com/index.html#section/Authentication
- type: Support
  url: https://alice.io/contact-us
- type: Blog
  url: https://alice.io/blog
- type: GitHubOrganization
  url: https://github.com/ActiveFence
- type: Login
  url: https://app.alice.io/
- type: TermsOfService
  url: https://alice.io/terms-of-use
- type: PrivacyPolicy
  url: https://alice.io/privacy-policy
- type: Postman
  url: https://www.postman.com/activefence-demo-team
- type: LLMsTxt
  url: llms/activefence-llms.txt
- type: Packages
  url: packages/activefence-packages.yml
- type: SDKs
  url: packages/activefence-packages.yml
- type: CLI
  url: cli/activefence-cli.yml
- type: Authentication
  url: authentication/activefence-authentication.yml
- type: Conventions
  url: conventions/activefence-conventions.yml
- type: ErrorCatalog
  url: errors/activefence-problem-types.yml
- type: Lifecycle
  url: lifecycle/activefence-lifecycle.yml
- type: Conformance
  url: conformance/activefence-conformance.yml
- type: Compliance
  url: conformance/activefence-conformance.yml
- type: DomainSecurity
  url: security/activefence-domain-security.yml
- type: WellKnown
  url: well-known/activefence-well-known.yml
- type: Webhooks
  url: asyncapi/activefence-webhooks.yml
- type: DataModel
  url: data-model/activefence-data-model.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Overlay
  url: overlays/activefence-alice-api-overlay.yaml

ActiveFence

Kin Score

APIs 7

ActiveFence api keys API

ActiveFence Collection API

ActiveFence Content API

ActiveFence Flags API

ActiveFence Users API

ActiveFence Wonder Build API

ActiveFence Wonder Fence API

Open Collections 8

API Collection

Alice API Documentation api keys API

Alice API Documentation Collection API

Alice API Documentation Content API

Alice API Documentation Flags API

Alice API Documentation Users API

Alice API Documentation Wonder Build API

Alice API Documentation Wonder Fence API

MCP Servers 1

activefence-mcp.yml

Event Specifications 1

Activefence Webhooks

Security Posture 2

Activefence Authentication

Activefence Domain Security

Agentic Access 1

Activefence Agentic Access