Horizon Robotics

Horizon Robotics (Hong Kong Stock Exchange: 9660.HK) is a Chinese provider of smart-driving computing solutions, founded in 2015, that designs the Journey (征程) family of automotive AI processors around its proprietary BPU (Brain Processing Unit) architecture and pairs them with a full software stack — Horizon Mono ADAS, Horizon SuperDrive assisted driving, TogetheROS, Matrix, QoHo and AIDI. Its developer-facing surface is not a hosted web API but a toolchain: OpenExplorer (OE), the model compilation, quantization and deployment kit built around HBDK, HMCT, the Horizon PyTorch Plugin, horizon_tc_ui and the UCP on-board runtime, documented at developer.horizon.auto and doc.oe.horizon.auto. Horizon publishes two genuine agent surfaces on top of that toolchain: a live, unauthenticated remote Model Context Protocol server at mcp.oe.horizon.auto that exposes semantic code and documentation retrieval, and OE-Skills, an Apache-2.0 pack of 37 structured Agent Skills for Claude Code, Codex and Cursor that drive HBDK compilation, PTQ/QAT quantization, UCP on-board inference and LLM compression.

Horizon Robotics is listed with 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Automotive, Autonomous Driving, and Semiconductors.

Horizon Robotics’ developer surface includes documentation, engineering blog, support, signup flow, CLI, authentication, changelog, and 22 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

28.8/100 thin ▬ flat Agent 27/100 agent aware Front door AI 1/6 silent Heartbeat 96/100 alive saas Full breakdown ↓
scored 2026-11-13 · rubric v0.28.0 · Show this score on your site →

1 API 1 MCP Servers

Company Artificial Intelligence Automotive Autonomous Driving Semiconductors Robotics Edge AI Machine Learning MCP Agent Skills Developer Tools China

Kin Score

Kin Score How this is scored →
scored 2026-11-13 · rubric v0.28.0

Composite quality — 28.8/100 · thin

Contract Quality 0.0 / 21

Developer Ergonomics 8.5 / 17

Access Clarity 4.0 / 17

Operational Transparency 3.2 / 11

Contract Governance 1.9 / 10

Discoverability 5.8 / 9

Regulatory Posture 3.7 / 15

Agent readiness — 27/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 9 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/horizon-robotics/"><img src="https://apis.io/badge/horizon-robotics/card.svg" alt="Horizon Robotics on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

Machine-Readable Contract +18 pts — api_specs includes an OpenAPI document Ask about this →
Agentic Access Contract +10 pts — agentic_access artifact present (x-agentic-access), graded by author Ask about this →
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0 Ask about this →
Request/Response Examples +7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link Ask about this →
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document Ask about this →
Delegated User Identity +6 pts — a served discovery document listing authorization_code in grant_types_supported (served), else an oauth2 authorizationCode flow or openIdConnect declared in an OpenAPI (documented) Ask about this →

7 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Contract Quality scores 0.0 — up to +25.0 composite points Ask about this →
Access Clarity scores 23.4 — up to +15.3 composite points Ask about this →
Developer Ergonomics scores 50.0 — up to +10.0 composite points Ask about this →

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Not sure how this applies to your stack? Ask about any one item. Kin Lane reads every question, looks at your profile and your situation, and replies with what a fix would take — scoped to that one area, priced up front, yours whether you ship it or not. Ask a question →

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/horizon-robotics/apis.yml: open an issue on github.com/api-evangelist/horizon-robotics to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
Agent Skills (SKILL.md packages)	undeclared	-	-	1
Autonomous Vehicles (self-driving testing, deployment, robotaxi service)	undeclared	-	-	1
Semiconductor Consortia (RISC-V, OCP hardware, CHIPS awards)	undeclared	-	-	1

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

Standards implemented 2

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

Agent Skills

measured — observed by APIs.io (published)

Model Context Protocol (MCP)

measured — observed by APIs.io (verified)

APIs 1

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

Open Explorer MCP Server

Horizon Robotics' hosted Model Context Protocol server for the OpenExplorer toolchain. Probed anonymously on 2026-08-22: MCP protocol version 2025-06-18, serverInfo "Open Explor...

MCP Servers 1

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

Open Explorer MCP Server

Horizon Robotics' hosted Model Context Protocol server for the OpenExplorer (OE) toolchain. It gives a coding agent semantic retrieval over Horizon's indexed codebases (Milvus-b...

MCP SERVER

Horizon Robotics API pricing

Pricing Plans 1

Published pricing tiers and plan structures.

Horizon Robotics Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Horizon Robotics Rate Limits

0 limits

RATE LIMITS

Privacy & Data 1

Its role, the data it processes, retention and transfers, quoted from its own privacy page.

Horizon Robotics

21 quoted statements, read from Horizon Robotics's own page on 2026-11-09.

PRIVACY

Security Posture 3

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

Horizon Robotics Authentication

1 scheme

SECURITY

Horizon Robotics Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Horizon Robotics Vulnerability Disclosure

contact published

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

SignUp

SignUp

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

AgentSkill

AgentSkill

MCPServer

MCPServer

LLMsTxt

LLMsTxt

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

Idempotency

ErrorCatalog

Lifecycle

Conformance

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

CLI

Packages

SDKs

Access & Security 4

Authentication, authorization, and security posture

Security

Security

VulnerabilityDisclosure

VulnerabilityDisclosure

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 3

Status, limits, changes, and where to get help

Support

Support

RateLimits

RateLimits

ChangeLog

ChangeLog

Commercial 2

Pricing, plans, and the legal terms of use

PrivacyPolicy

PrivacyPolicy

Plans

Plans

Company 3

The organization behind the API

BlogRSS

BlogRSS

Website

Website

Blog

Blog

Other 2

Properties that don't map to a standard resource type

IntellectualProperty

IntellectualProperty

DataProcessing

DataProcessing

Source (apis.yml)

aid: horizon-robotics
name: Horizon Robotics
description: 'Horizon Robotics (Hong Kong Stock Exchange: 9660.HK) is a Chinese provider of smart-driving computing solutions,
  founded in 2015, that designs the Journey (征程) family of automotive AI processors around its proprietary BPU (Brain Processing
  Unit) architecture and pairs them with a full software stack — Horizon Mono ADAS, Horizon SuperDrive assisted driving, TogetheROS,
  Matrix, QoHo and AIDI. Its developer-facing surface is not a hosted web API but a toolchain: OpenExplorer (OE), the model
  compilation, quantization and deployment kit built around HBDK, HMCT, the Horizon PyTorch Plugin, horizon_tc_ui and the
  UCP on-board runtime, documented at developer.horizon.auto and doc.oe.horizon.auto. Horizon publishes two genuine agent
  surfaces on top of that toolchain: a live, unauthenticated remote Model Context Protocol server at mcp.oe.horizon.auto that
  exposes semantic code and documentation retrieval, and OE-Skills, an Apache-2.0 pack of 37 structured Agent Skills for Claude
  Code, Codex and Cursor that drive HBDK compilation, PTQ/QAT quantization, UCP on-board inference and LLM compression.'
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - rate-limits
  - security
  generated: '2026-11-13'
  method: derived
image: https://www.horizon.auto/favicon.ico
url: https://raw.githubusercontent.com/api-evangelist/horizon-robotics/refs/heads/main/apis.yml
x-type: company
x-source: harvest:secondary-market
specificationVersion: '0.20'
created: '2026-08-22'
modified: '2026-10-06'
tags:
- Company
- Artificial Intelligence
- Automotive
- Autonomous Driving
- Semiconductors
- Robotics
- Edge AI
- Machine Learning
- MCP
- Agent Skills
- Developer Tools
- China
tags_raw:
- Company
- Artificial Intelligence
- Automotive
- Autonomous Driving
- Semiconductors
- Robotics
- Edge AI
- Machine Learning
- Model Context Protocol
- Agent Skills
- Developer Tools
- China
- Machine-Learning
apis:
- name: Open Explorer MCP Server
  description: 'Horizon Robotics'' hosted Model Context Protocol server for the OpenExplorer toolchain. Probed anonymously
    on 2026-08-22: MCP protocol version 2025-06-18, serverInfo "Open Explorer MCP Server" v3.9.0, four read-only tools (list_codebases,
    search_code, search_doc, get_doc) providing semantic retrieval over indexed Horizon codebases and the Horizon documentation
    library, plus three MCP resources. No authentication is required.'
  humanURL: https://github.com/HorizonRobotics/OE-Skills
  baseURL: https://mcp.oe.horizon.auto/mcp
  tags:
  - MCP
  - Developer Tools
  - Documentation
  - Code Search
  tags_raw:
  - Model Context Protocol
  - Developer Tools
  - Documentation
  - Code Search
  properties:
  - type: MCPServer
    url: mcp/horizon-robotics-mcp.yml
  - type: Authentication
    url: authentication/horizon-robotics-authentication.yml
  - type: ErrorCatalog
    url: errors/horizon-robotics-problem-types.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- url: https://www.horizon.auto/rss.xml
  type: BlogRSS
- type: Website
  url: https://www.horizon.auto/en
- type: DeveloperPortal
  url: https://developer.horizon.auto/
- type: Documentation
  url: https://developer.horizon.auto/docs
- type: Blog
  url: https://developer.horizon.auto/blog
- type: Support
  url: https://developer.horizon.auto/forum
- type: SignUp
  url: https://developer.horizon.auto/login
- type: GitHubOrganization
  url: https://github.com/HorizonRobotics
- type: PrivacyPolicy
  url: https://www.horizon.auto/en/legal/privacy
- type: IntellectualProperty
  url: https://www.horizon.auto/en/legal/intellectual-property-rights
- type: Security
  url: security/horizon-robotics-vulnerability-disclosure.yml
- type: VulnerabilityDisclosure
  url: security/horizon-robotics-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/horizon-robotics-domain-security.yml
- type: AgentSkill
  url: skills/_index.yml
- type: MCPServer
  url: mcp/horizon-robotics-mcp.yml
- type: CLI
  url: cli/horizon-robotics-cli.yml
- type: Packages
  url: packages/horizon-robotics-packages.yml
- type: SDKs
  url: packages/horizon-robotics-packages.yml
- type: Conventions
  url: conventions/horizon-robotics-conventions.yml
- type: Idempotency
  url: conventions/horizon-robotics-conventions.yml
- type: ErrorCatalog
  url: errors/horizon-robotics-problem-types.yml
- type: Lifecycle
  url: lifecycle/horizon-robotics-lifecycle.yml
- type: Conformance
  url: conformance/horizon-robotics-conformance.yml
- type: Authentication
  url: authentication/horizon-robotics-authentication.yml
- type: RateLimits
  url: rate-limits/horizon-robotics-rate-limits.yml
- type: Plans
  url: plans/horizon-robotics-plans-pricing.yml
- type: ChangeLog
  url: changelog/horizon-robotics-changelog.yml
- type: LLMsTxt
  url: llms/horizon-robotics-llms.txt
- type: DataProcessing
  url: privacy/horizon-robotics-privacy-policy.yml
x-enrichment:
  date: '2026-08-22'
  status: enriched
  artifacts_added: 20
  pass: local-v1

Horizon Robotics API — frequently asked questions

Does Horizon Robotics have an API?

Yes. APIs.io lists 1 API from Horizon Robotics, including Open Explorer MCP Server.

How do I authenticate with the Horizon Robotics API?

Horizon Robotics uses bearer-token authentication (1 scheme). The details are profiled on APIs.io as Horizon Robotics Authentication.

Does Horizon Robotics have an MCP server?

Yes. APIs.io lists 1 MCP server for Horizon Robotics: Horizon Robotics' hosted Model Context Protocol server for the OpenExplorer (OE) toolchain. It gives a coding agent semantic retrieval over Horizon's indexed codebases (Milvus-backed) and the Horizon

Is the Horizon Robotics API ready for AI agents?

Horizon Robotics has a Kin Score of 28.8 out of 100 (thin) and an Agent Readiness score of 26.6 (agent-aware), scored by API Evangelist on 2026-11-13.

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/horizon-robotics"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/horizon-robotics/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/horizon-robotics/evidence"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.