# Anthropic — API Agent Score

> Score: 79/100 (Grade: B) | Domain: anthropic.com | Rubric: 1.0.0 | Checked: July 21, 2026

Anthropic scored 79/100 (B), classified "partially-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/anthropic)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 79/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 89/100 (A)
- Developer Experience: 55/100 (D)
- Agent Discovery: 74/100 (B)
- Agent Understanding: 81/100 (A)
- Agent Usability: 92/100 (A+)

## Check Results

### API Design

- [pass] Auth declared & discoverable — authentication documented in the docs site at https://platform.claude.com/docs/en/manage-claude/authentication. Investigated: docs 100%, spec 50%.
- [warn] Schema coverage & depth — 3440/3462 (99%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 100%, spec 50%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [warn] Machine-readable, versioned contract — No info.version and no versioning scheme detected. Investigated: spec 50%, docs 0%.
- [pass] Example coverage — Code samples in 8 language(s) across docs (top: http, csharp, go); 0/19 pages have ≥ 2 languages on the same page. Investigated: docs 100%, sdk 100%, spec 0%.

### Developer Experience

- [pass] Code samples in docs — Code samples in 8 language(s) across docs (top: http, csharp, go); 0/19 pages have ≥ 2 languages on the same page. Investigated: docs 100%.
- [pass] Changelog published — changelog documented in the docs site at https://platform.claude.com/docs/en/release-notes/overview. Investigated: spec 100%, docs 100%, sdk 100%.
- [warn] Description completeness — 341/866 operations lack a description. Investigated: sdk 61%, spec 0%.
- [fail] Self-service developer portal — No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%.
- [fail] Quickstart present — No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (simonw/llm-anthropic, 78 snippets). Investigated: docs 100%, cli 100%, sdk 58%.
- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/1 pages return markdown); 1 returned error pages. Investigated: docs 75%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt directive found in HTML of any of 1 pages. Investigated: docs 30%, sdk 0%.
- [warn] Crawlable / AEO — Sitemap present (4111 entries) but carries no lastmod values. Investigated: wellknown 75%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — 15 distinct 4xx/5xx response codes documented. Investigated: docs 100%, sdk 100%, spec 50%.
- [pass] Operation purpose clarity — 97% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Agent-navigable, token-efficient docs — No pages support .md URLs (0/1 tested). Investigated: docs 88%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 19 sampled pages — likely a CSR-only docs site. Investigated: docs 0%.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Rate-limit signaling — rate-limit behavior documented in the docs site at https://platform.claude.com/docs/en/manage-claude/rate-limits-api. Investigated: spec 100%, docs 100%.
- [pass] Pagination documented & consistent — Pagination params detected on 27 list endpoint(s). Investigated: spec 100%, docs 100%, sdk 0%.
- [pass] Sandbox separation — sandbox documented in the docs site at https://platform.claude.com/docs/en/managed-agents/cloud-sandboxes-reference. Investigated: spec 100%, docs 100%, sdk 100%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

Anthropic's API program shows strong fundamentals in design and discoverability, but two areas are holding back partner and agent success: developer onboarding is largely self-service-free and lacks a quickstart, making the first-call experience slow and friction-heavy; and agent-facing context — executable examples, structured instructions, and machine-readable doc formats — is missing, leaving AI agents to guess at integration patterns. Closing these gaps should be the immediate priority to unlock both human partner velocity and reliable agent-driven integrations.