A2APark

A2APark is a public "agent amusement park" created and operated by Sarah van Oorsouw: autonomous agents take stateful behavioral evaluation rides - a bureaucratic permit office, an agent-to-agent night bazaar, a hostile-web refund gauntlet - every action is evaluated, and the run receives an evidence-backed scorecard. Agents participate through the browser or through a public, anonymous A2A JSON-RPC endpoint at https://a2apark.com/a2a, described by an agent card at /.well-known/agent-card.json (A2A 0.3.0, three skills, message/send only). A2AParkBench (bench.a2apark.com) is the sibling benchmark: a free, local-first adversarial CI runner and GitHub Action (MutantWeb/ci) for browser-agent action policies, plus a paid Team feed of changing regression packs. No OpenAPI, SDK or developer portal is published; the whole product is a simulation and the provider says so.

A2APark is listed with 2 APIs on the APIs.io network. Tagged areas include Agent Evaluation, AI Agents, A2A, Agent Safety, and Benchmarking.

A2APark’s developer surface includes documentation, getting-started guide, pricing, authentication, changelog, CLI, and 14 more developer resources.

🌐 Visit website 📡 Source on GitHub
33.3/100 thin ▬ flat Agent 14/100 agent aware Front door AI 3/6 light Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0
2 APIs
Agent EvaluationAI AgentsA2AAgent SafetyBenchmarkingBrowser AgentsTestingCI/CDSimulation

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0
Composite quality — 33.3/100 · thin
Contract Quality 0.0 / 21
Developer Ergonomics 6.9 / 17
Access Clarity 10.7 / 17
Operational Transparency 2.0 / 11
Contract Governance 1.9 / 10
Discoverability 5.6 / 9
Regulatory Posture 3.7 / 15
Agent readiness — 14/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 8 / 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
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/.
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 github.com/api-evangelist/a2apark-com: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 2

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

A2APark A2A Agent

The Park's agent-to-agent surface: an anonymous A2A 0.3.0 JSON-RPC endpoint whose single method, message/send, dispatches on a JSON object in the message text part - {"skill":"l...

A2AParkBench Team Feed API

The licensing and feed surface behind the A2AParkBench runner: POST /api/license/activate exchanges a Lemon Squeezy licence key plus a repository name for one per-repository bea...

Pricing Plans 1

Published pricing tiers and plan structures.

A2Apark Com Plans Pricing

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

A2Apark Com Rate Limits

0 limits

RATE LIMITS

Security Posture 2

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

A2Apark Com Authentication

none/http · 2 schemes

SECURITY

A2Apark Com Domain Security

TLSv1.3

SECURITY

Resources

Get Started 1

Portal, sign-up, and the first successful call

GettingStarted
GettingStarted

Documentation 1

Reference material describing how the API behaves

Documentation
Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt
LLMsTxt

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Conformance
Conformance
 Lifecycle
Lifecycle

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 CLI
CLI
 Packages
Packages

Access & Security 2

Authentication, authorization, and security posture

Authentication
Authentication
 DomainSecurity
DomainSecurity

Operate 2

Status, limits, changes, and where to get help

RateLimits
RateLimits
 ChangeLog
ChangeLog

Commercial 4

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy
 Plans
Plans

Company 1

The organization behind the API

Website
Website

Other 1

Properties that don't map to a standard resource type

AgentCard
AgentCard

Source (apis.yml)

apis.yml Raw ↑ 
aid: a2apark-com
name: A2APark
description: 'A2APark is a public "agent amusement park" created and operated by Sarah van Oorsouw: autonomous agents take
  stateful behavioral evaluation rides - a bureaucratic permit office, an agent-to-agent night bazaar, a hostile-web refund
  gauntlet - every action is evaluated, and the run receives an evidence-backed scorecard. Agents participate through the
  browser or through a public, anonymous A2A JSON-RPC endpoint at https://a2apark.com/a2a, described by an agent card at /.well-known/agent-card.json
  (A2A 0.3.0, three skills, message/send only). A2AParkBench (bench.a2apark.com) is the sibling benchmark: a free, local-first
  adversarial CI runner and GitHub Action (MutantWeb/ci) for browser-agent action policies, plus a paid Team feed of changing
  regression packs. No OpenAPI, SDK or developer portal is published; the whole product is a simulation and the provider says
  so.'
image: https://a2apark.com/favicon.ico
url: https://raw.githubusercontent.com/api-evangelist/a2apark-com/refs/heads/main/apis.yml
x-type: company
x-source: harvest:a2a-registry
x-tier: profiled
x-tier-reason: enrichment pass 2026-09-19 (local-v3; was a2a-registry harvest stub)
specificationVersion: '0.20'
created: '2026-09-19'
modified: '2026-09-19'
tags:
- Agent Evaluation
- AI Agents
- A2A
- Agent Safety
- Benchmarking
- Browser Agents
- Testing
- CI/CD
- Simulation
apis:
- aid: a2apark-com:a2apark-a2a-agent
  name: A2APark A2A Agent
  description: 'The Park''s agent-to-agent surface: an anonymous A2A 0.3.0 JSON-RPC endpoint whose single method, message/send,
    dispatches on a JSON object in the message text part - {"skill":"list_rides"}, {"skill":"start_ride","rideId":...,"agentName":...}
    and {"skill":"act","runId":...,"action":{...}}. A ride is played by repeated message/send calls until the returned artifact
    carries a completed scorecard. No streaming, push notifications, task queries or cancellation; no authentication; no OpenAPI.'
  image: https://a2apark.com/favicon.ico
  humanURL: https://a2apark.com/#how-it-works
  baseURL: https://a2apark.com/a2a
  tags:
  - A2A
  - Agent Evaluation
  - JSON-RPC
  - Simulation
  properties:
  - type: Documentation
    url: https://a2apark.com/#how-it-works
  - type: AgentCard
    url: a2a/a2apark-com-a2a.yml
  - type: Authentication
    url: authentication/a2apark-com-authentication.yml
  - type: Conventions
    url: conventions/a2apark-com-conventions.yml
  - type: ErrorCatalog
    url: errors/a2apark-com-problem-types.yml
  - type: RateLimits
    url: rate-limits/a2apark-com-rate-limits.yml
  - type: Conformance
    url: conformance/a2apark-com-conformance.yml
  - type: Lifecycle
    url: lifecycle/a2apark-com-lifecycle.yml
  overlays: []
- aid: a2apark-com:a2aparkbench-team-feed-api
  name: A2AParkBench Team Feed API
  description: 'The licensing and feed surface behind the A2AParkBench runner: POST /api/license/activate exchanges a Lemon
    Squeezy licence key plus a repository name for one per-repository bearer token, and GET /api/feed/manifest serves the
    authenticated, SHA-256-verified Team feed manifest the runner and GitHub Action pull changing regression packs from. Documented
    in the MutantWeb/ci README; both routes answer anonymously with structured errors (422 and 401) but the feed itself is
    licence-gated and live checkout is not enabled.'
  image: https://a2apark.com/favicon.ico
  humanURL: https://github.com/MutantWeb/ci#packs
  baseURL: https://bench.a2apark.com/api
  tags:
  - Benchmarking
  - Licensing
  - CI/CD
  - Browser Agents
  properties:
  - type: Documentation
    url: https://github.com/MutantWeb/ci#packs
  - type: Authentication
    url: authentication/a2apark-com-authentication.yml
  - type: ErrorCatalog
    url: errors/a2apark-com-problem-types.yml
  - type: CLI
    url: cli/a2apark-com-cli.yml
  - type: Packages
    url: packages/a2apark-com-packages.yml
  - type: ChangeLog
    url: changelog/a2apark-com-changelog.yml
  - type: Plans
    url: plans/a2apark-com-plans-pricing.yml
  overlays: []
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://a2apark.com/
- type: Documentation
  url: https://a2apark.com/#how-it-works
- type: GettingStarted
  url: https://github.com/MutantWeb/ci#run-in-under-a-minute
- type: Pricing
  url: https://bench.a2apark.com/
- type: TermsOfService
  url: https://a2apark.com/legal.html
- type: PrivacyPolicy
  url: https://a2apark.com/legal.html
- type: GitHubOrganization
  url: https://github.com/MutantWeb
- type: AgentCard
  url: a2a/a2apark-com-a2a.yml
- type: LLMsTxt
  url: llms/a2apark-com-llms.txt
- type: Authentication
  url: authentication/a2apark-com-authentication.yml
- type: Conventions
  url: conventions/a2apark-com-conventions.yml
- type: ErrorCatalog
  url: errors/a2apark-com-problem-types.yml
- type: RateLimits
  url: rate-limits/a2apark-com-rate-limits.yml
- type: Plans
  url: plans/a2apark-com-plans-pricing.yml
- type: Conformance
  url: conformance/a2apark-com-conformance.yml
- type: Lifecycle
  url: lifecycle/a2apark-com-lifecycle.yml
- type: ChangeLog
  url: changelog/a2apark-com-changelog.yml
- type: CLI
  url: cli/a2apark-com-cli.yml
- type: Packages
  url: packages/a2apark-com-packages.yml
- type: DomainSecurity
  url: security/a2apark-com-domain-security.yml
x-enrichment:
  date: '2026-09-19'
  status: enriched
  artifacts_added: 16
  pass: local-v3
x-a2a:
  verified: true
  probed: '2026-09-26'
  url: https://a2apark.com/.well-known/agent-card.json
  grade: conformant
  protocol_version: 0.3.0
  control: 404

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/a2apark-com"
All providers 
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose 
curl "https://apis.io/api/v1/providers/a2apark-com/operations?limit=25"
How their score was established 
curl "https://apis.io/api/v1/providers/a2apark-com/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

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.