Arthur AI
Arthur is an enterprise AI governance and observability platform for discovering, monitoring, evaluating, and governing AI and ML systems in production. The Arthur Platform API (internally "Arthur Scope", OpenAPI 3.1) exposes 213 operations across models, tasks, datasets, connectors, metrics, alerts, alert rules, policies, workspaces, projects, agents, and webhooks, secured with OAuth2 via Keycloak. Arthur also ships the open-source Arthur Engine (LLM guardrails plus ML evaluation), the arthur-bench LLM evaluation library, Python client SDKs, and an Agent Toolkit with a Claude Code integration for end-to-end tracing.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles Arthur AI the way a machine reads it — 35 machine-readable artifacts across 30 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Arthur AI scores 51.9/100 (developing), with a separate agent-readiness read of 61/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Arthur AI
Each block below is one kind of artifact we hold for Arthur AI. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 30
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Arthur AI Agents V1 API
The Agents V1 API from Arthur AI — 12 operation(s) for agents v1.
Arthur AI Alert Rules V1 API
The Alert Rules V1 API from Arthur AI — 5 operation(s) for alert rules v1.
Arthur AI Alerts V1 API
The Alerts V1 API from Arthur AI — 5 operation(s) for alerts v1.
Arthur AI Authorization V1 API
The Authorization V1 API from Arthur AI — 9 operation(s) for authorization v1.
Arthur AI Connector Schemas V1 API
The Connector Schemas V1 API from Arthur AI — 2 operation(s) for connector schemas v1.
Arthur AI Connectors V1 API
The Connectors V1 API from Arthur AI — 4 operation(s) for connectors v1.
Arthur AI Custom Aggregation Tests V1 API
The Custom Aggregation Tests V1 API from Arthur AI — 3 operation(s) for custom aggregation tests v1.
Arthur AI Custom Aggregations V1 API
The Custom Aggregations V1 API from Arthur AI — 3 operation(s) for custom aggregations v1.
Arthur AI Data Plane Associations V1 API
The Data Plane Associations V1 API from Arthur AI — 4 operation(s) for data plane associations v1.
Arthur AI Data Planes V1 API
The Data Planes V1 API from Arthur AI — 4 operation(s) for data planes v1.
Arthur AI Data Retrieval V1 API
The Data Retrieval V1 API from Arthur AI — 4 operation(s) for data retrieval v1.
Arthur AI Datasets V1 API
The Datasets V1 API from Arthur AI — 9 operation(s) for datasets v1.
Arthur AI Feature Flags V1 API
The Feature Flags V1 API from Arthur AI — 1 operation(s) for feature flags v1.
Arthur AI Groups V1 API
The Groups V1 API from Arthur AI — 4 operation(s) for groups v1.
Arthur AI Health API
The Health API from Arthur AI — 1 operation(s) for health.
Arthur AI Jobs V1 API
The Jobs V1 API from Arthur AI — 7 operation(s) for jobs v1.
Arthur AI Metric Functions V1 API
The Metric Functions V1 API from Arthur AI — 1 operation(s) for metric functions v1.
Arthur AI Metrics V1 API
The Metrics V1 API from Arthur AI — 3 operation(s) for metrics v1.
Arthur AI Models V1 API
The Models V1 API from Arthur AI — 7 operation(s) for models v1.
Arthur AI OAuth V1 API
The OAuth V1 API from Arthur AI — 1 operation(s) for oauth v1.
Arthur AI Organizations V1 API
The Organizations V1 API from Arthur AI — 1 operation(s) for organizations v1.
Arthur AI Policies V1 API
The Policies V1 API from Arthur AI — 22 operation(s) for policies v1.
Arthur AI Projects V1 API
The Projects V1 API from Arthur AI — 2 operation(s) for projects v1.
Arthur AI Registration V1 API
The Registration V1 API from Arthur AI — 1 operation(s) for registration v1.
Arthur AI Roles V1 API
The Roles V1 API from Arthur AI — 1 operation(s) for roles v1.
Arthur AI Tasks V1 API
The Tasks V1 API from Arthur AI — 7 operation(s) for tasks v1.
Arthur AI Upsolve V1 API
The Upsolve V1 API from Arthur AI — 1 operation(s) for upsolve v1.
Arthur AI Users V1 API
The Users V1 API from Arthur AI — 8 operation(s) for users v1.
Arthur AI Webhooks V1 API
The Webhooks V1 API from Arthur AI — 3 operation(s) for webhooks v1.
Arthur AI Workspaces V1 API
The Workspaces V1 API from Arthur AI — 3 operation(s) for workspaces v1.
Scroll within the panel for all 30 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
arthur-ai-mcp.yml
MCP SERVEREvent Specifications 1
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
Arthur Ai Webhooks
ASYNCAPISecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Scopes 1
OAuth scopes are the vocabulary of least-privilege access. Profiling them shows exactly what an integration — or an agent acting on a user's behalf — is allowed to do.
OAuth scopes governing access to this provider's APIs.
Resources
Every other property we hold for Arthur AI — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 3
Portal, sign-up, and the first successful call
Documentation 1
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 3
Authentication, authorization, and security posture
Operate 3
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 1
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/arthur-ai · machine-readable index on apis.io