# Neo4j — API Agent Score

> Score: 74/100 (Grade: B) | Domain: neo4j.com | Rubric: 1.0.0 | Checked: July 24, 2026

Neo4j scored 74/100 (B), classified "partially-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/neo4j)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 74/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 87/100 (A)
- Developer Experience: 47/100 (F)
- Agent Discovery: 78/100 (B)
- Agent Understanding: 80/100 (A)
- Agent Usability: 74/100 (B)

## Check Results

### API Design

- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: docs 100%, spec 50%, wellknown 0%.
- [warn] Machine-readable, versioned contract — info.version="v2beta1" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%.
- [warn] Schema coverage & depth — 78% of operations have documented schemas (target 95%+). Investigated: spec 67%, sdk 60%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, spec 0%.

### Developer Experience

- [pass] Changelog published — Newest official SDK activity 1 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.
- [warn] Description completeness — 381/723 operations lack a description. Investigated: sdk 47%, 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%.
- [skip] Code samples in docs — No surface produced evidence for this capability in this run.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (websites/neo4j, 2310 snippets). Investigated: docs 100%, cli 100%, sdk 67%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt directive found in HTML of any of 49 sampled pages; 1 failed to fetch. Investigated: docs 83%, sdk 0%.
- [warn] Docs reachable, not hard auth-gated — All 50 sampled pages require authentication. Investigated: docs 60%.
- [warn] Crawlable / AEO — No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 25%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — 11 distinct 4xx/5xx response codes documented. Investigated: docs 100%, sdk 100%, spec 50%.
- [pass] Operation purpose clarity — 100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Agent-navigable, token-efficient docs — Could not fetch HTML for any pages to compare; 1 failed to fetch. Investigated: docs 75%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (spec, sdk) is 3% (threshold 35% for full credit).
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Docs structured data — No surface produced evidence for this capability in this run.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Pagination documented & consistent — Pagination params detected on 20 list endpoint(s). Investigated: spec 100%, docs 100%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%.
- [fail] Rate-limit signaling — No rate-limit response headers documented. Investigated: spec 0%, docs 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

Neo4j's API design and agent-readable contract are strong foundations — but the partner program has two critical gaps that will cost you integrations. There is no self-service portal or quickstart, meaning partners hit a wall before writing their first call, and there is no machine-readable agent context (AGENTS.md) or runnable collection, leaving AI coding agents without the structured guidance they need to integrate correctly. Fixing self-service onboarding and agent-ready context first will unlock faster partner activation and reliable agent-driven integrations.