Agent Bench

Agent Bench operates agenthaven.dev, a DNSSEC-signed zone that publishes AI agents through DNS-AID, and runs one live agent in it: the Agent Bench Travel Merchant at travel.agenthaven.dev — a proof-of-concept seller agent that quotes real flight fares (Google Flights via SerpApi) and turns a chosen quote into a Stripe test-mode payment intent under a buyer-supplied spending mandate. It is reachable over A2A (JSON-RPC 0.3, agent card at the canonical well-known path, pinned by SHA-256 digest and ES256 signature in the DNS SVCB record) and MCP (2025-06-18, two tools with full input and output schemas, anonymous tools/list). It publishes a SPIFFE JWT-SVID for the running instance, DANE TLSA pins, an ARD trust catalog, a GoDaddy ANS registration and a public hash-chained ledger of every quote, refusal and checkout. No OpenAPI, no SDKs, no pricing; no real money moves and no ticket is issued.

Agent Bench is listed with 1 API on the APIs.io network. Tagged areas include Agents, A2A, MCP, Agentic Commerce, and DNS-AID.

Agent Bench’s developer surface includes documentation, authentication, sandbox, and 16 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

17.9/100 emerging ▬ flat Agent 29/100 agent aware Front door AI 3/6 light Full breakdown ↓
scored 2026-10-31 · rubric v0.25.0 · Show this score on your site →

1 API 1 MCP Servers 1 Agent Skills

Agents A2A MCP Agentic CommerceDNS-AIDTravel Flights Payments Agent Identity Proof of Concept Agent-Native

Kin Score

Kin Score How this is scored →
scored 2026-10-31 · rubric v0.25.0

Composite quality — 17.9/100 · emerging

Contract Quality 0.0 / 21

Developer Ergonomics 5.2 / 17

Access Clarity 0.0 / 17

Operational Transparency 3.5 / 11

Contract Governance 1.9 / 10

Discoverability 5.2 / 9

Regulatory Posture 2.3 / 15

Agent readiness — 29/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 10 / 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 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

Pagination 5 / 5

Distinct Operations 3 / 3

Regulatory Posture applies to this provider. Its tags matched the Payments 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/agenthaven-dev/"><img src="https://apis.io/badge/agenthaven-dev/card.svg" alt="Agent Bench 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
Request/Response Examples +7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link
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)
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document
Typed Event Surface +6 pts — AsyncAPI document, OR webhooks/callbacks objects in the as-published OpenAPI, OR common[].type includes Webhooks
Documented Reversibility +6 pts — a reversal operation in the contract, graded up when a window is documented too

5 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
Access Clarity scores 0.0 — up to +20.0 composite points
Developer Ergonomics scores 30.4 — up to +13.9 composite points

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.

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/agenthaven-dev/apis.yml: open an issue on github.com/api-evangelist/agenthaven-dev 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 →

APIs 1

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

Agent Bench Travel Merchant

Seller agent for flight search and travel checkout, exposed on one host through two protocol doors: A2A JSON-RPC 0.3 at https://travel.agenthaven.dev/a2a (message/send with a Da...

MCP Servers 1

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

Agent Bench MCP Server

Agent Bench operates ONE remote MCP server at https://travel.agenthaven.dev/mcp, on the same host as its A2A JSON-RPC endpoint (/a2a) and its documentation. It is POST-only Stre...

MCP SERVER

Agent Skills 1

Packaged agent skills for driving this provider's APIs from an AI assistant.

agenthaven-dev-search-and-checkout

AGENT SKILL

Pricing Plans 1

Published pricing tiers and plan structures.

Agenthaven Dev Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Agenthaven Dev Rate Limits

3 limits

RATE LIMITS

Security Posture 2

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

Agenthaven Dev Authentication

none/http-bearer-jwt · 2 schemes

SECURITY

Agenthaven Dev Domain Security

TLSv1.3 · DNSSEC · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Agenthaven Dev Agentic Access

2 operations · 1 acting · 1 human-in-the-loop

2 operations · 1 acting

AGENTIC

Resources

Get Started 1

Portal, sign-up, and the first successful call

Sandbox

Sandbox

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

MCPServer

AgenticAccess

WellKnown

LLMsTxt

AgentSkill

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conventions

Idempotency

ErrorCatalog

DataModel

Conformance

Lifecycle

Access & Security 2

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

RateLimits

RateLimits

Commercial 1

Pricing, plans, and the legal terms of use

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)

aid: agenthaven-dev
name: Agent Bench
description: 'Agent Bench operates agenthaven.dev, a DNSSEC-signed zone that publishes AI agents through DNS-AID, and runs
  one live agent in it: the Agent Bench Travel Merchant at travel.agenthaven.dev — a proof-of-concept seller agent that quotes
  real flight fares (Google Flights via SerpApi) and turns a chosen quote into a Stripe test-mode payment intent under a buyer-supplied
  spending mandate. It is reachable over A2A (JSON-RPC 0.3, agent card at the canonical well-known path, pinned by SHA-256
  digest and ES256 signature in the DNS SVCB record) and MCP (2025-06-18, two tools with full input and output schemas, anonymous
  tools/list). It publishes a SPIFFE JWT-SVID for the running instance, DANE TLSA pins, an ARD trust catalog, a GoDaddy ANS
  registration and a public hash-chained ledger of every quote, refusal and checkout. No OpenAPI, no SDKs, no pricing; no
  real money moves and no ticket is issued.'
url: https://raw.githubusercontent.com/api-evangelist/agenthaven-dev/refs/heads/main/apis.yml
x-type: company
x-source: harvest:a2a-registry
x-tier: profiled
x-tier-reason: 'Full local enrichment pass 2026-09-19 (was: stub / harvest). Conformant A2A agent card, live anonymous MCP
  server, DNS-AID/DNSSEC/DANE discovery and a public audit ledger found on travel.agenthaven.dev; no OpenAPI.'
specificationVersion: '0.20'
created: '2026-09-19'
modified: '2026-09-19'
tags:
- Agents
- A2A
- MCP
- Agentic Commerce
- DNS-AID
- Travel
- Flights
- Payments
- Agent Identity
- Proof of Concept
- Agent-Native
tags_raw:
- Agents
- A2A
- MCP
- Agentic Commerce
- DNS-AID
- Travel
- Flights
- Payments
- Agent Identity
- Proof of Concept
- agent-native
apis:
- aid: agenthaven-dev:agent-bench-travel-merchant
  name: Agent Bench Travel Merchant
  description: 'Seller agent for flight search and travel checkout, exposed on one host through two protocol doors: A2A JSON-RPC
    0.3 at https://travel.agenthaven.dev/a2a (message/send with a DataPart {action, input} or a one-line TextPart) and MCP
    2025-06-18 at https://travel.agenthaven.dev/mcp (initialize, ping, tools/list, tools/call). Two operations, called in
    order: search_flights (anonymous; IATA codes and an ISO date in, up to two signed quotes valid ten minutes out — cheapest
    and fastest, with itinerary and EUR fare in minor units) and create_checkout (bearer JWT under a spending mandate; turns
    one quote into a Stripe test-mode payment intent and stops — no ticket, no real money). Every response carries a request
    id and an evidence block naming the merchant, the card digest and the SPIFFE signer; every call is written to the public
    hash-chained ledger at /ledger. No OpenAPI: the machine-readable contract is tools/list.'
  humanURL: https://travel.agenthaven.dev/
  baseURL: https://travel.agenthaven.dev
  tags:
  - A2A
  - MCP
  - Travel
  - Flights
  - Agentic Commerce
  - Agent-Native
  tags_raw:
  - A2A
  - MCP
  - Travel
  - Flights
  - Agentic Commerce
  - agent-native
  properties:
  - type: Documentation
    url: https://travel.agenthaven.dev/
  - type: AgentCard
    url: a2a/agenthaven-dev-a2a.yml
  - type: AgentCard
    name: A2A Agent Card (provider-hosted)
    url: https://travel.agenthaven.dev/.well-known/agent-card.json
  - type: MCPServer
    url: mcp/agenthaven-dev-mcp.yml
  - type: MCPServer
    name: MCP endpoint (Streamable HTTP, POST only)
    url: https://travel.agenthaven.dev/mcp
  - type: A2A
    name: A2A JSON-RPC endpoint (POST only, message/send)
    url: https://travel.agenthaven.dev/a2a
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://agenthaven.dev/
- type: Documentation
  url: https://travel.agenthaven.dev/
- type: AgentCard
  url: a2a/agenthaven-dev-a2a.yml
- type: MCPServer
  url: mcp/agenthaven-dev-mcp.yml
- type: AgenticAccess
  url: agentic-access/agenthaven-dev-agentic-access.yml
- type: WellKnown
  url: well-known/agenthaven-dev-well-known.yml
- type: LLMsTxt
  url: llms/agenthaven-dev-llms.txt
- type: Authentication
  url: authentication/agenthaven-dev-authentication.yml
- type: Conventions
  url: conventions/agenthaven-dev-conventions.yml
- type: Idempotency
  url: conventions/agenthaven-dev-conventions.yml
- type: ErrorCatalog
  url: errors/agenthaven-dev-problem-types.yml
- type: DataModel
  url: data-model/agenthaven-dev-data-model.yml
- type: RateLimits
  url: rate-limits/agenthaven-dev-rate-limits.yml
- type: Plans
  url: plans/agenthaven-dev-plans-pricing.yml
- type: Sandbox
  url: sandbox/agenthaven-dev-sandbox.yml
- type: Conformance
  url: conformance/agenthaven-dev-conformance.yml
- type: Lifecycle
  url: lifecycle/agenthaven-dev-lifecycle.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DomainSecurity
  url: security/agenthaven-dev-domain-security.yml
x-enrichment:
  date: '2026-09-19'
  status: enriched
  artifacts_added: 26
  pass: local-v3
x-a2a:
  verified: true
  probed: '2026-09-26'
  url: https://travel.agenthaven.dev/.well-known/agent-card.json
  grade: conformant
  protocol_version: '0.3'
  control: 404

Agent Bench API — frequently asked questions

Does Agent Bench have an API?

Yes. APIs.io lists 1 API from Agent Bench, including Agent Bench Travel Merchant.

How do I authenticate with the Agent Bench API?

Agent Bench uses bearer-token authentication (none/http-bearer-jwt · 2 schemes). The details are profiled on APIs.io as Agenthaven Dev Authentication.

Does Agent Bench have an MCP server?

Yes. APIs.io lists 1 MCP server for Agent Bench: Agent Bench operates ONE remote MCP server at https://travel.agenthaven.dev/mcp, on the same host as its A2A JSON-RPC endpoint (/a2a) and its documentation. It is POST-only Streamable HTTP without ser

Is the Agent Bench API ready for AI agents?

Agent Bench has a Kin Score of 17.9 out of 100 (emerging) and an Agent Readiness score of 28.5 (agent-aware), scored by API Evangelist on 2026-10-31.

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/agenthaven-dev"

All providers

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

Every operation they expose

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

How their score was established

curl "https://apis.io/api/v1/providers/agenthaven-dev/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.