H2O.ai
H2O.ai is an open-source artificial-intelligence and machine-learning company whose platform spans H2O-3 (a distributed, in-memory ML engine), H2O Driverless AI (automatic machine learning), H2O MLOps (model deployment, scoring and monitoring), H2O Wave (a Python/R framework for realtime AI apps), H2O LLM Studio, and Enterprise h2oGPTe (a private generative-AI, RAG and agent platform). Enterprise h2oGPTe publishes a 422-operation OpenAPI 3.0.1 contract covering collections, document ingestion, chat, agents, extractors, GraphRAG, guardrails, models, permissions and scheduled tasks, and H2O MLOps publishes an OpenAPI contract for its model-scoring endpoints. H2O.ai also ships a first-party MCP server that proxies the h2oGPTe REST API to agent clients, together with official Python, R, Java and JavaScript client libraries distributed via PyPI, CRAN, Maven Central and npm.
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 H2O.ai the way a machine reads it — 58 machine-readable artifacts across 26 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 — H2O.ai scores 54.1/100 (developing), with a separate agent-readiness read of 43/100 (agent ready). 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 2026-08-17 · rubric v0.11.0
Put this on your own site. The badge is drawn live from H2O.ai's current Kin Score — paste it once and it updates itself every time the score is recomputed. It follows your visitor's light or dark setting, and it links back here so anyone who sees it can read the full breakdown.
<!-- Kin Score · API Evangelist -->
<a href="https://providers.apievangelist.com/providers/h2o-ai/"
title="H2O.ai on API Evangelist — API profile and Kin Score">
<img src="https://apis.io/badge/h2o-ai.svg"
alt="H2O.ai Kin Score — API readiness rating by API Evangelist" width="150" height="150" loading="lazy">
</a>[](https://providers.apievangelist.com/providers/h2o-ai/)<!-- Kin Score · API Evangelist -->
<a href="https://providers.apievangelist.com/providers/h2o-ai/"
title="H2O.ai on API Evangelist — API profile and Kin Score">
<img src="https://apis.io/badge/h2o-ai/card.svg"
alt="H2O.ai Kin Score — API readiness rating by API Evangelist" width="340" height="120" loading="lazy">
</a>More shapes, themes and sizes → · Score as JSON · How badges work
How we profile H2O.ai
Each block below is one kind of artifact we hold for H2O.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 26
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.
h2oGPTe MCP Server
H2OGPTe MCP Server is H2O.ai's first-party Model Context Protocol server for Enterprise h2oGPTe. It runs locally over stdio and proxies traffic to the h2oGPTe REST API, generati...
H2O.ai Admin Sessions API
The Admin Sessions API from H2O.ai — 3 operation(s) for admin sessions.
H2O.ai Agents API
The Agents API from H2O.ai — 30 operation(s) for agents.
H2O.ai AI Assistants API
The AI Assistants API from H2O.ai — 30 operation(s) for ai assistants.
H2O.ai API Keys API
The API Keys API from H2O.ai — 5 operation(s) for api keys.
H2O.ai Chat API
The Chat API from H2O.ai — 29 operation(s) for chat.
H2O.ai Collections API
The Collections API from H2O.ai — 40 operation(s) for collections.
H2O.ai Configurations API
The Configurations API from H2O.ai — 12 operation(s) for configurations.
H2O.ai Document Ingestion API
The Document Ingestion API from H2O.ai — 21 operation(s) for document ingestion.
H2O.ai Documents API
The Documents API from H2O.ai — 20 operation(s) for documents.
H2O.ai Extractors API
The Extractors API from H2O.ai — 10 operation(s) for extractors.
H2O.ai Forums API
The Forums API from H2O.ai — 9 operation(s) for forums.
H2O.ai Graph RAG API
The GraphRAG API from H2O.ai — 4 operation(s) for graphrag.
H2O.ai Guardrails API
The Guardrails API from H2O.ai — 4 operation(s) for guardrails.
H2O.ai Jobs API
The Jobs API from H2O.ai — 6 operation(s) for jobs.
H2O.ai Memory Blocks API
The Memory Blocks API from H2O.ai — 9 operation(s) for memory blocks.
H2O.ai Model API
The Model API from H2O.ai — 7 operation(s) for model.
H2O.ai Models API
The Models API from H2O.ai — 19 operation(s) for models.
H2O.ai Permissions API
The Permissions API from H2O.ai — 24 operation(s) for permissions.
H2O.ai Prompt Templates API
The Prompt Templates API from H2O.ai — 11 operation(s) for prompt templates.
H2O.ai Scheduled Tasks API
The Scheduled Tasks API from H2O.ai — 13 operation(s) for scheduled tasks.
H2O.ai Secrets API
The Secrets API from H2O.ai — 4 operation(s) for secrets.
H2O.ai Shared Chats API
The Shared Chats API from H2O.ai — 3 operation(s) for shared chats.
H2O.ai Showcase API
The Showcase API from H2O.ai — 5 operation(s) for showcase.
H2O.ai System API
The System API from H2O.ai — 3 operation(s) for system.
H2O.ai Tags API
The Tags API from H2O.ai — 3 operation(s) for tags.
Scroll within the panel for all 26 ·
Open Collections 26
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
API Collection
OPEN COLLECTIONh2oGPTe REST Admin Sessions API
OPEN COLLECTIONh2oGPTe REST Agents API
OPEN COLLECTIONh2oGPTe REST AI Assistants API
OPEN COLLECTIONh2oGPTe REST API Keys API
OPEN COLLECTIONh2oGPTe REST Chat API
OPEN COLLECTIONh2oGPTe REST Collections API
OPEN COLLECTIONh2oGPTe REST Configurations API
OPEN COLLECTIONh2oGPTe REST Document Ingestion API
OPEN COLLECTIONh2oGPTe REST Documents API
OPEN COLLECTIONh2oGPTe REST Extractors API
OPEN COLLECTIONh2oGPTe REST Forums API
OPEN COLLECTIONh2oGPTe REST Graph RAG API
OPEN COLLECTIONh2oGPTe REST Guardrails API
OPEN COLLECTIONh2oGPTe REST Jobs API
OPEN COLLECTIONh2oGPTe REST Memory Blocks API
OPEN COLLECTIONMLOps Scoring REST Model API
OPEN COLLECTIONh2oGPTe REST Models API
OPEN COLLECTIONh2oGPTe REST Permissions API
OPEN COLLECTIONh2oGPTe REST Prompt Templates API
OPEN COLLECTIONh2oGPTe REST Scheduled Tasks API
OPEN COLLECTIONh2oGPTe REST Secrets API
OPEN COLLECTIONh2oGPTe REST Shared Chats API
OPEN COLLECTIONh2oGPTe REST Showcase API
OPEN COLLECTIONh2oGPTe REST System API
OPEN COLLECTIONh2oGPTe REST Tags API
OPEN COLLECTIONScroll within the panel for all 26 ·
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.
h2o-ai-mcp.yml
MCP SERVERSecurity Posture 4
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.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for H2O.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 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 5
Pagination, idempotency, versioning, errors, and events
Build 4
SDKs, sample code, and the tooling you integrate with
Access & Security 6
Authentication, authorization, and security posture
Operate 5
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
Other 1
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/h2o-ai · machine-readable index on apis.io
This is an independent, third-party profile of H2O.ai, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.