SafetyKit

SafetyKit is an AI trust, safety, and fraud-detection platform that lets marketplaces, fintechs, and social and creator platforms deploy AI agents to automate risk reviews, onboarding, and investigations. Its Data API ingests every user action and object through a lightweight SDK and API, organizes them into per-workflow namespaces, and asynchronously returns agent decisions — labels, risk scores, and enforcement actions such as account suspension — delivered back over signed webhooks. SafetyKit detects account takeover, multi-accounting, fake accounts, phishing, spam, harmful content, scams, and prohibited listings, and is used by companies including Upwork, Etsy, Eventbrite, Lyft, Discord, and Kickstarter.

SafetyKit publishes 1 API on the APIs.io network. Tagged areas include Company, Ai, Trust and Safety, Fraud Detection, and Content Moderation.

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

SafetyKit’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, signup flow, authentication, and 21 more developer resources.

43.4/100 thin ▬ flat Agent 43/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
1 APIs 1 MCP Servers
CompanyAiTrust and SafetyFraud DetectionContent ModerationRiskAI AgentsCompliance

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 43.4/100 · thin
Contract Quality 5.7 / 25
Developer Ergonomics 14.8 / 20
Commercial Clarity 10.0 / 20
Operational Transparency 3.8 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 43/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 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
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/safetykit: 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.

SafetyKit Data API

Ingest user actions and objects into per-workflow namespaces and asynchronously receive AI agent decisions (labels, risk scores, enforcement actions) via signed webhooks.

MCP Servers 1

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

safetykit-mcp.yml

MCP SERVER

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Security Posture 3

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

Safetykit Authentication

http · 1 scheme

SECURITY

Safetykit Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Safetykit Trust Center

SOC 2, HIPAA, GDPR

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Build 3

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: safetykit
name: SafetyKit
description: SafetyKit is an AI trust, safety, and fraud-detection platform that lets marketplaces, fintechs, and social and
  creator platforms deploy AI agents to automate risk reviews, onboarding, and investigations. Its Data API ingests every
  user action and object through a lightweight SDK and API, organizes them into per-workflow namespaces, and asynchronously
  returns agent decisions — labels, risk scores, and enforcement actions such as account suspension — delivered back over
  signed webhooks. SafetyKit detects account takeover, multi-accounting, fake accounts, phishing, spam, harmful content, scams,
  and prohibited listings, and is used by companies including Upwork, Etsy, Eventbrite, Lyft, Discord, and Kickstarter.
url: https://raw.githubusercontent.com/api-evangelist/safetykit/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- ribbit-capital
x-tier: stub
x-tier-reason: portfolio-lead
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
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
image: https://cdn.prod.website-files.com/67f043481889440b9d0ed13e/67f043481889440b9d0ed170_a5826400373f60a9d521bc5bca8ad3f3_OG%20Image.jpg
tags:
- Company
- Ai
- Trust and Safety
- Fraud Detection
- Content Moderation
- Risk
- AI Agents
- Compliance
apis:
- name: SafetyKit Data API
  description: Ingest user actions and objects into per-workflow namespaces and asynchronously receive AI agent decisions
    (labels, risk scores, enforcement actions) via signed webhooks.
  humanURL: https://docs.safetykit.com/
  baseURL: https://api.safetykit.com
  tags:
  - Trust and Safety
  - Fraud Detection
  - Risk
  properties:
  - type: Documentation
    url: https://docs.safetykit.com/
  - type: APIReference
    url: https://docs.safetykit.com/api
  - type: Authentication
    url: https://docs.safetykit.com/authentication
  - type: Webhooks
    url: https://docs.safetykit.com/webhooks/introduction
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: TrustCenter
  url: security/safetykit-trust-center.yml
- type: DomainSecurity
  url: security/safetykit-domain-security.yml
- type: Website
  url: https://www.safetykit.com
- type: DeveloperPortal
  url: https://docs.safetykit.com/
- type: Documentation
  url: https://docs.safetykit.com/
- type: APIReference
  url: https://docs.safetykit.com/api
- type: GettingStarted
  url: https://docs.safetykit.com/using-data-api/copy-and-paste-quickstart
- type: Support
  url: mailto:support@safetykit.com
- type: Blog
  url: https://safetykit.com/news
- type: GitHubOrganization
  url: https://github.com/GetSafetyKit
- type: SignUp
  url: https://app.safetykit.com/
- type: TermsOfService
  url: https://app.safetykit.com/msa_2024-03-25.pdf
- type: PrivacyPolicy
  url: https://app.safetykit.com/privacy.pdf
- type: Compliance
  url: security/safetykit-trust-center.yml
- type: StatusPage
  url: http://www.safetykitstatus.com/
- type: Lifecycle
  url: lifecycle/safetykit-lifecycle.yml
- type: Authentication
  url: authentication/safetykit-authentication.yml
- type: Conventions
  url: conventions/safetykit-conventions.yml
- type: Webhooks
  url: asyncapi/safetykit-webhooks.yml
- type: ErrorCatalog
  url: errors/safetykit-problem-types.yml
- type: DataModel
  url: data-model/safetykit-data-model.yml
- type: Conformance
  url: conformance/safetykit-conformance.yml
- type: Packages
  url: packages/safetykit-packages.yml
- type: SDKs
  url: packages/safetykit-packages.yml
- type: MCPServer
  url: mcp/safetykit-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: WellKnown
  url: well-known/safetykit-well-known.yml
- type: LLMsTxt
  url: llms/safetykit-llms.txt
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 15
  pass: local-v1