Agentcard

Agentcard is a Y Combinator (Summer 2026) startup building card-issuing payments infrastructure for AI agents. It issues virtual Visa cards that are funded with a fixed USD amount and close after their first charge, giving agents scoped, single-use spending power with hard budget limits and no overdraft risk. Access is available three ways over one host: a REST v2 API, a hosted Model Context Protocol (MCP) server, and first-party CLIs. There are two products: Personal (an individual gives their own agent a card, funded via Apple Pay / Google Pay) and Companies ("Connect with Agentcard" — a platform issues cards to many users through OAuth 2.1 + PKCE). The platform covers user connect, identity verification (KYC), wallet funding, withdrawals, virtual card creation, transactions, and merchant shopping (buy) with HMAC-signed webhooks and a sandbox mode split from live by credential.

Agentcard publishes 5 API contracts indexed on the APIs.io network, including Authentication API, Connect API, Identity verification API, and 2 more. Tagged areas include Company, Payments, Virtual Cards, Card Issuing, and AI Agents.

The Agentcard catalog on APIs.io includes 2 event-driven AsyncAPI specifications and 1 Spectral governance ruleset.

Agentcard’s developer surface includes documentation, API reference, getting-started guide, quickstart, support, engineering blog, pricing, and 34 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

55.2/100 strong ▬ flat Agent 72/100 agent native Front door AI 5/6 prominent saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

1 published contract 1 MCP Servers 4 Agent Skills

Company Payments Virtual Cards Card Issuing AI Agents Agentic Commerce MCP Fintech Wallets Visa A2A

What this lets a business do 2

Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →

Agent Infrastructure & Agentic Commerce

AE-100

Member cardsPurchase

POST /buy GET /buy/merchants GET /buy/orders/{order_id} POST /api/v2/cards

Application Identity & Verification

AE-160

Identity Verification

POST /api/v2/kyc/documents/front GET /api/v2/kyc POST /api/v2/kyc/import

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 55.2/100 · strong

Contract Quality 11.5 / 19

Developer Ergonomics 13.6 / 15

Access Clarity 6.7 / 15

Operational Transparency 2.6 / 10

Contract Governance 1.6 / 9

Discoverability 5.6 / 8

Regulatory Posture 3.3 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 72/100 · agent native

Machine-Readable Contract 18 / 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 7 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 4 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 8 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 6 / 6

Protected Resource Metadata 5 / 5

Registration Without a Human 6 / 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 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 applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% 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/agentcard/"><img src="https://apis.io/badge/agentcard/card.svg" alt="Agentcard 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):

Rate-Limit Signaling +7 pts — OpenAPI responses document X-RateLimit-* / RateLimit headers (verified), else a rate_limits artifact or RateLimits link (documented)
Documented Reversibility +6 pts — a reversal operation in the contract, graded up when a window is documented too
Agentic Commerce Well-Known Document +5 pts — a parsing /.well-known/ucp.json or acp.json declaring a version and at least one service, OR (0.27) a live x402 payment challenge from _data/x402-adoption.json — `self` when its endpoints are on the provider's own domain, `platform` when they are on a vendor's
Dry-Run / Simulate Mode +4 pts — OpenAPI: destructive operations expose a dry_run / simulate / preview / validate_only parameter
Consent & Bot Identity +3 pts — common[].type includes AIPREF, ContentSignal, WebBotAuth, or HTTPMessageSignatures

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

Access Clarity scores 44.7 — up to +11.1 composite points
Contract Governance scores 18.2 — up to +9.8 composite points
Contract Quality scores 61.4 — up to +9.7 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/agentcard/apis.yml: open an issue on github.com/api-evangelist/agentcard 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
AI Agents (A2A agent cards)	undeclared	-	1	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 8

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.

Agent2Agent

measured — observed by APIs.io (flavored)

Model Context Protocol (MCP)

measured — observed by APIs.io (verified)

Agent Skills

measured — observed by APIs.io (published)

OAuth 2.0 Protected Resource Metadata

measured — observed by APIs.io (verified)

Dynamic Client Registration

measured — observed by APIs.io (published)

OpenAPI

measured — observed by APIs.io (published)

OAuth 2.0

measured — observed by APIs.io (declared)

Universal Commerce Protocol (UCP)

measured — observed by APIs.io (self)

APIs 5

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

Agentcard Authentication API

Exchange your client credentials for a platform access token, and introspect what a token acts as.

Agentcard Connect API

Connect a user to your platform: send a one-time code, verify it, record consent, and keep the connection alive.

Agentcard Identity verification API

Verify a connected user's identity: upload their ID, submit any extra fields we ask for, then show a short face scan.

Agentcard Member cards API

The Member cards API from Agentcard — 4 operation(s) for member cards.

Agentcard Purchase API

The Purchase API from Agentcard — 4 operation(s) for purchase.

Open Collections 5

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

Agentcard Authentication API

OPEN COLLECTION

Agentcard Authentication Connect API

OPEN COLLECTION

Agentcard Authentication Identity verification API

OPEN COLLECTION

Agentcard Authentication Wallet funding API

OPEN COLLECTION

Agentcard Authentication Withdrawals API

OPEN COLLECTION

Arazzo Workflows 2

Multi-step API workflows described with the Arazzo specification.

Agentcard — connect a user and verify identity

Connect an end user, record consent, and run identity verification (KYC) end to end.

ARAZZO

Agentcard — verify phone and fund wallet

Verify a user's phone, create an Apple/Google Pay funding session, and poll it to completion.

ARAZZO

MCP Servers 1

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

Agentcard

Virtual Visa cards for AI agents with MCP-native spending controls and per-task budget limits.

MCP SERVER

Agent Skills 4

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

Connect and consent a user

AGENT SKILL

Fund a user's wallet

AGENT SKILL

agent-card

AGENT SKILL

Verify a user's identity (KYC)

AGENT SKILL

Service Levels 1

Uptime the provider promises or reports, as SLA4OAI. Read from its own pages; APIs.io runs no monitors.

Agentcard

SLA

Event Specifications 2

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Agentcard Webhooks

Event notifications Agentcard delivers to destinations you register in the dashboard. Every delivery is a POST with a signed envelope { id, type, created, livemode, data }. Veri...

ASYNCAPI

Agentcard Webhooks

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Agentcard API Rules

58 rules · 51 errors 5 warnings 2 info

SPECTRAL

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Agentcard V2 Overlay

3 actions · update · agentcard-openapi-original.json

DERIVED

Security Posture 2

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

Agentcard Authentication

http/oauth2 · 2 schemes

SECURITY

Agentcard Domain Security

TLSv1.3 · DMARC

SECURITY

Agentic Access 1

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

Agentcard Agentic Access

21 operations · 15 acting

AGENTIC

Resources

Get Started 5

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

Quickstart

SignUp

Sandbox

Documentation 3

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

AsyncAPI

AsyncAPI

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

MCPServer

LLMsTxt

WellKnown

AgentSkill

Design & Contract 9

Pagination, idempotency, versioning, errors, and events

ErrorCatalog

Conventions

Idempotency

Lifecycle

Conformance

DataModel

Webhooks

Arazzo

Arazzo

Scroll for all 9

Build 6

SDKs, sample code, and the tooling you integrate with

PostmanWorkspace

PostmanWorkspace

GitHubOrganization

Postman

Packages

SDKs

CLI

Access & Security 2

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 2

Status, limits, changes, and where to get help

Support

Support

StatusPage

StatusPage

Commercial 3

Pricing, plans, and the legal terms of use

Pricing

Pricing

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 4

Properties that don't map to a standard resource type

CapabilityMap

Overlay

AgentCard

APICatalog

Source (apis.yml)

aid: agentcard
name: Agentcard
description: 'Agentcard is a Y Combinator (Summer 2026) startup building card-issuing payments infrastructure for AI agents.
  It issues virtual Visa cards that are funded with a fixed USD amount and close after their first charge, giving agents scoped,
  single-use spending power with hard budget limits and no overdraft risk. Access is available three ways over one host: a
  REST v2 API, a hosted Model Context Protocol (MCP) server, and first-party CLIs. There are two products: Personal (an individual
  gives their own agent a card, funded via Apple Pay / Google Pay) and Companies ("Connect with Agentcard" — a platform issues
  cards to many users through OAuth 2.1 + PKCE). The platform covers user connect, identity verification (KYC), wallet funding,
  withdrawals, virtual card creation, transactions, and merchant shopping (buy) with HMAC-signed webhooks and a sandbox mode
  split from live by credential.'
url: https://raw.githubusercontent.com/api-evangelist/agentcard/refs/heads/main/apis.yml
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - 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
  - security
  - sandbox
  generated: '2026-11-06'
  method: derived
image: https://www.agentcard.sh/favicon.ico
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: profiled
x-tier-reason: enriched-from-portfolio-lead
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-17'
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-09-17
tags:
- Company
- Payments
- Virtual Cards
- Card Issuing
- AI Agents
- Agentic Commerce
- MCP
- Fintech
- Wallets
- Visa
- A2A
tags_raw:
- Company
- Payments
- Virtual Cards
- Card Issuing
- AI Agents
- Agentic Commerce
- MCP
- Fintech
- Wallet
- Visa
- A2A
apis:
- aid: agentcard:agentcard-authentication-api
  name: Agentcard Authentication API
  description: Exchange your client credentials for a platform access token, and introspect what a token acts as.
  humanURL: https://docs.agentcard.sh/companies/api/overview
  baseURL: https://api.agentcard.sh
  tags:
  - Authentication
  properties:
  - type: OpenAPI
    url: openapi/agentcard-authentication-api-openapi.yml
- aid: agentcard:agentcard-connect-api
  name: Agentcard Connect API
  description: 'Connect a user to your platform: send a one-time code, verify it, record consent, and keep the connection
    alive.'
  humanURL: https://docs.agentcard.sh/companies/api/overview
  baseURL: https://api.agentcard.sh
  tags:
  - Connect
  properties:
  - type: OpenAPI
    url: openapi/agentcard-connect-api-openapi.yml
- aid: agentcard:agentcard-identity-verification-api
  name: Agentcard Identity verification API
  description: 'Verify a connected user''s identity: upload their ID, submit any extra fields we ask for, then show a short
    face scan.'
  humanURL: https://docs.agentcard.sh/companies/api/overview
  baseURL: https://api.agentcard.sh
  tags:
  - Identity Verification
  tags_raw:
  - Identity verification
  properties:
  - type: OpenAPI
    url: openapi/agentcard-identity-verification-api-openapi.yml
- aid: agentcard:agentcard-member-cards-api
  name: Agentcard Member cards API
  description: The Member cards API from Agentcard — 4 operation(s) for member cards.
  humanURL: https://docs.agentcard.sh/companies/api/overview
  baseURL: https://api.agentcard.sh
  tags:
  - Member cards
  properties:
  - type: OpenAPI
    url: openapi/agentcard-member-cards-api-openapi.yml
- aid: agentcard:agentcard-purchase-api
  name: Agentcard Purchase API
  description: The Purchase API from Agentcard — 4 operation(s) for purchase.
  humanURL: https://docs.agentcard.sh/companies/api/overview
  baseURL: https://api.agentcard.sh
  tags:
  - Purchase
  properties:
  - type: OpenAPI
    url: openapi/agentcard-purchase-api-openapi.yml
common:
- type: CapabilityMap
  url: capabilities/agentcard-capability-edges.yml
  name: Agentcard Business Capability Map
- type: PostmanWorkspace
  url: https://www.postman.com/kinlaneapi/agentcard/overview
- type: Overlay
  url: overlays/agentcard-v2-overlay.yaml
- type: AgentCard
  url: a2a/agentcard-a2a.yml
  name: A2A Agent Card
  description: Agent Card served at /.well-known/agent-card.json (flavored against A2A 1.0.0).
- type: Website
  url: https://www.agentcard.sh
- type: DeveloperPortal
  url: https://docs.agentcard.sh
- type: Documentation
  url: https://docs.agentcard.sh
- type: APIReference
  url: https://docs.agentcard.sh/companies/api/reference
- type: GettingStarted
  url: https://docs.agentcard.sh/companies/getting-started/quickstart
- type: Quickstart
  url: https://docs.agentcard.sh/personal/quickstart
- type: Support
  url: https://docs.agentcard.sh/personal/support
- type: Blog
  url: https://www.agentcard.sh/blog/
- type: GitHubOrganization
  url: https://github.com/agentcard
- type: Pricing
  url: https://docs.agentcard.sh/personal/plans
- type: SignUp
  url: https://app.agentcard.sh
- type: TermsOfService
  url: https://www.agentcard.sh/terms
- type: PrivacyPolicy
  url: https://www.agentcard.sh/privacy
- type: Postman
  url: https://docs.agentcard.sh/companies/api/postman
- type: StatusPage
  url: https://agentcard.checkly-status-page.com
- type: Authentication
  url: authentication/agentcard-authentication.yml
- type: AgenticAccess
  url: agentic-access/agentcard-agentic-access.yml
- type: DomainSecurity
  url: security/agentcard-domain-security.yml
- type: Packages
  url: packages/agentcard-packages.yml
- type: SDKs
  url: packages/agentcard-packages.yml
- type: CLI
  url: cli/agentcard-cli.yml
- type: MCPServer
  url: mcp/agentcard-mcp.yml
- type: LLMsTxt
  url: llms/agentcard-llms.txt
- type: WellKnown
  url: well-known/agentcard-well-known.yml
- type: APICatalog
  url: well-known/agentcard-api-catalog.json
- type: ErrorCatalog
  url: errors/agentcard-problem-types.yml
- type: Conventions
  url: conventions/agentcard-conventions.yml
- type: Idempotency
  url: conventions/agentcard-conventions.yml
- type: Lifecycle
  url: lifecycle/agentcard-lifecycle.yml
- type: Sandbox
  url: sandbox/agentcard-sandbox.yml
- type: Conformance
  url: conformance/agentcard-conformance.yml
- type: DataModel
  url: data-model/agentcard-data-model.yml
- type: AsyncAPI
  url: asyncapi/agentcard-webhooks-asyncapi.yml
- type: Webhooks
  url: asyncapi/agentcard-webhooks.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Arazzo
  name: Connect a user and verify identity
  url: arazzo/agentcard-connect-and-verify.arazzo.yml
- type: Arazzo
  name: Verify phone and fund wallet
  url: arazzo/agentcard-fund-wallet.arazzo.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Agentcard API — frequently asked questions

Does Agentcard have an API?

Yes. APIs.io lists 5 APIs from Agentcard, including Agentcard Authentication API, Agentcard Connect API and Agentcard Identity verification API, and 2 more.

Is there an OpenAPI specification for the Agentcard API?

Yes. APIs.io indexes 5 OpenAPI specifications for Agentcard, each linked for download from this page.

How do I authenticate with the Agentcard API?

Agentcard documents its authentication (http/oauth2 · 2 schemes). The details are profiled on APIs.io as Agentcard Authentication.

Does Agentcard have an MCP server?

Yes. APIs.io lists 1 MCP server for Agentcard: Virtual Visa cards for AI agents with MCP-native spending controls and per-task budget limits.

Is the Agentcard API ready for AI agents?

Agentcard has a Kin Score of 55.2 out of 100 (strong) and an Agent Readiness score of 72.3 (agent-native), scored by API Evangelist on 2026-11-06.

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/agentcard"

All providers

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

Every operation they expose

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

How their score was established

curl "https://apis.io/api/v1/providers/agentcard/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.