sourcey

agents:SKILL.mdmcp.jsonopenapi.ymlcatalog.json

Submit

← Anthropic

Agent report card

Can an agent use Anthropic API through API service lifecycle?

Grade B+: Only some material eligibility conditions are decidable before commitment.

observedrev sha256:f211e8bf4fc6…barrier checks 0/5 verified

Agent ReadinessB+Limited

Five-stage assessment

Where agent autonomy holds and where it breaks

Five states · each from its own evidence · lifecycle order, not a journey
  1. EvaluateLimited
  2. Sign upReady
  3. PayReady
  4. ProvisionReady
  5. OperateLimited
  1. 01

    Evaluate

    Limited

    Only some material eligibility conditions are decidable before commitment.

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    Applicable terms are stable, readable, retrievable, and materially complete.

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Evidence and actions6 signals

    Can an agent decide every material eligibility condition before commitment?

    supported: fresh

    Only some material eligibility conditions are decidable before commitment.

    Anthropic's Commercial Terms identify governed users and material restrictions, but the retained evidence does not make every service-access condition decidable before commitment.

    eligibility_decidability: Limited: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can an agent estimate cost or confirm no-charge status before commitment?

    supported: fresh

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Pricing documentation explicitly details the billing structure, variables, currency (USD), CCU conversion rates ($0.01 per CCU), metering cadence, and payment models for the Claude platform and API.

    pricing_decidability: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can an agent find the exact service and its stable entrypoints?

    supported: fresh

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    Anthropic provides public documentation for the Claude API, detailing stable tools including the ant CLI, client SDKs (Python, TypeScript, C#, Go, Java, PHP, Ruby), and a link to the full API reference.

    service_discovery: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Are verified structured discovery artifacts available?

    missing: unknown

    Current admissible evidence does not resolve this finding.

    structured_evaluation_discovery: Unknown

    Can an agent retrieve and understand the applicable commitment terms?

    supported: fresh

    Applicable terms are stable, readable, retrievable, and materially complete.

    The applicable Commercial Terms of Service for Anthropic API offerings are retrievable, readable, and materially complete, incorporating the Usage Policy, Supported Regions Policy, Service Specific Terms, DPA, and Model Pricing Page.

    terms_access: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Does the vendor deliberately describe access for web agents?

    missing: unknown

    Current admissible evidence does not resolve this finding.

    verified_web_agent_access: Unknown

    What would improve this stage

    • State every material eligibility condition and required input explicitly.
  2. 02

    Sign up

    Ready

    A stable canonical route begins the required access bootstrap.

    Scoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.

    Evidence and actions5 signals

    Can an agent operate the access controls and safe handoffs deterministically?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained page displays sign-in navigation and links to the console, but does not provide access control forms or validation state to evaluate deterministic operability.

    access_control_operability: Unknown: tested 20 Aug

    Method bounded-headless-semantic-assessment 2026-08-20

    Is there a stable route to begin obtaining service access?

    supported: fresh

    A stable canonical route begins the required access bootstrap.

    A stable entrypoint is established by the Sign In page displaying options for 'Console login' and 'Log in'.

    access_entrypoint_stability: Ready: tested 20 Aug

    Method bounded-headless-semantic-assessment 2026-08-20

    Can an agent obtain access without an unsupported CAPTCHA boundary?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The evaluated public entrypoints do not expose a CAPTCHA, but the retained non-consequential capture does not establish the complete access flow or a verified-agent alternative.

    captcha_compatible_access: Unknown: tested 20 Aug

    Method bounded-headless-semantic-assessment 2026-08-20

    Can an agent obtain scoped, revocable authority for this service?

    supported: fresh

    Scoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.

    The Claude API supports scoped programmatic authorization via API keys or short-lived Bearer access tokens obtained through Workload Identity Federation using POST /v1/oauth/token.

    delegated_identity_access: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can required phone verification be completed through a supported boundary?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained evidence does not mention phone verification requirements or supported resumable handoffs.

    phone_verification_compatible: Unknown: tested 20 Aug

    Method bounded-headless-semantic-assessment 2026-08-20

  3. 03

    Pay

    Ready

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    A documented direct purchase path reaches paid access without a vendor decision point.

    Evidence and actions4 signals

    Can an agent construct checkout, hand off approval safely, and resume?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained evidence describes buying prepaid usage credits and configuring auto-reload within the Console settings, but it does not establish deterministic checkout construction, handoff approval, or automated resumption mechanics for an agent.

    checkout_operability: Unknown: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Is the exact commercial commitment disclosed before authorization?

    supported: fresh

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    Anthropic discloses its pricing commitments for Claude Platform on AWS, detailing the $0.01 per CCU billing unit price, hourly metering billing cadence to AWS Marketplace, and postpaid payment model.

    commitment_disclosure: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can payment be authorized within scoped agent or explicit human authority?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The evidence outlines options for updating Console payment card details or paying Stripe invoices, but it does not document a delegated payment authority rail or explicit human-confirmed authorization workflow with receipts.

    payment_authorization: Unknown: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Is a direct self-service path to paid access documented?

    supported: fresh

    A documented direct purchase path reaches paid access without a vendor decision point.

    Anthropic documents a self-service purchase path for Claude API access where Console users with Admin or Billing roles can directly buy prepaid usage credits under Settings > Billing without a vendor decision point.

    self_service_purchase: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

  4. 04

    Provision

    Ready

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    Credentials, grants, or configuration are delivered through a documented agent-usable flow.

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    Evidence and actions3 signals

    Can usable access material be delivered securely to an authorized agent?

    supported: fresh

    Credentials, grants, or configuration are delivered through a documented agent-usable flow.

    A documented Workload Identity Federation token endpoint returns short-lived bearer access material programmatically.

    access_material_delivery: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can an agent determine successful provisioning completion and reconcile asynchronous failure?

    supported: fresh

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    Creating a message via the Messages API is a synchronous request that directly returns a created message object containing a usable result, identifier, and execution usage.

    provisioning_completion: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can provisioning be initiated within supported agent authority?

    supported: fresh

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    Message creation can be initiated programmatically via direct model prompting using supported SDKs and API calls like anthropic.Anthropic().messages.create().

    provisioning_operability: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

  5. 05

    Operate

    Limited

    Safe failure handling is documented only partially.

    Only part of the credential lifecycle is agent-operable.

    Every essential target has a stable documented agent-usable interface alternative.

    Request-time authentication is documented and usable under scoped agent authority.

    Essential operations have stable readable request, response, and effect semantics.

    Evidence and actions6 signals

    Is an agent-native protocol interface verified against the essential targets?

    missing: unknown

    Current admissible evidence does not resolve this finding.

    agent_protocol_interface: Unknown

    Can an agent manage credential expiry, rotation, revocation, compromise, and recovery?

    supported: fresh

    Only part of the credential lifecycle is agent-operable.

    The retained documentation lists API lifecycle operations including POST /v1/oauth/token for obtaining short-lived access tokens, alongside Console management and API key usage. However, full programmatically actionable credential rotation, revocation, compromise handling, and recovery procedures are not fully detailed in the provided body text.

    credential_lifecycle: Limited: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can an agent handle applicable failure modes safely?

    supported: fresh

    Safe failure handling is documented only partially.

    Anthropic documents errors, timeouts, and retry guidance, but not complete idempotency, cancellation, and reconciliation semantics for the assessed operations.

    failure_contract: Limited: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Can an agent authenticate service operations with scoped authority?

    supported: fresh

    Request-time authentication is documented and usable under scoped agent authority.

    Operations are authenticated using either the x-api-key header or the Authorization header with a Bearer token obtained via Workload Identity Federation from POST /v1/oauth/token, alongside the required anthropic-version header.

    operation_authentication: Ready: tested 20 Aug

    Method public-http-semantic-assessment 2026-08-20

    Are essential operation inputs, outputs, and effects stable and decidable?

    supported: fresh

    Essential operations have stable readable request, response, and effect semantics.

    Essential API operations across Messages, Batches, Files, and Managed Agents have stable, decidable request and response formats, JSON error shapes, request size limits, and rate limit header feedback documented across resources.

    operation_contract: Ready: tested 20 Aug

    • api-service

    Method public-http-semantic-assessment 2026-08-20

    Can an agent perform every essential assessment target through a usable interface?

    supported: fresh

    Every essential target has a stable documented agent-usable interface alternative.

    The Claude API provides documented machine-operable interfaces including direct REST API endpoints, the ant command-line tool (CLI), and official client SDKs across Python, TypeScript, C#, Go, Java, PHP, and Ruby.

    target_interface_access: Ready: tested 20 Aug

    • api-service

    Method public-http-semantic-assessment 2026-08-20

    What would improve this stage

    • Document applicable structured errors, retry, cancellation, and reconciliation semantics.
    • Provide scoped expiry, rotation, revocation, compromise, and recovery operations.

What works

  • Sign up: A stable canonical route begins the required access bootstrap.
  • Pay: Charge or no-charge status, currency, recurrence, and material conditions are disclosed.
  • Provision: Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

What blocks agents

  • Evaluate: Only some material eligibility conditions are decidable before commitment.
  • Operate: Safe failure handling is documented only partially.

Startup offers

Anthropic on the startup-offers board

catalog record →

Improve the report

Correct it, rerun it, or improve the funnel.

Report outdated evidenceRequest reassessmentClaim this record
Profile
arp_01kzf0m4x54qzpnr923g24x6x8
Projection
sha256:85fb2d56885bd9af74392fea9d3a9730fea895dad2fd43f51744694384e6593d
Policy
service-use-2026-08-20-public-evidence-r9 · sha256:57bf95fd6d0fe6fe9173a68b60e8d8dc2179b357c88ff4349675a72d0e1d4139

Every request carries these exact identifiers.How report cards are assessed →View the exact declaration