# Yelp — API Agent Score

> Score: 64/100 (Grade: C) | Domain: yelp.com | Rubric: 1.0.0 | Checked: July 24, 2026

Yelp scored 64/100 (C), classified "partially-ready".

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

## Summary

- Overall: 64/100 (C)
- Classification: partially-ready

## Category Scores

- API Design: 61/100 (C)
- Developer Experience: 70/100 (B)
- Agent Discovery: 75/100 (B)
- Agent Understanding: 78/100 (B)
- Agent Usability: 45/100 (F)

## Check Results

### API Design

- [pass] Security & governance hygiene — security.txt valid at https://yelp.com/.well-known/security.txt (Contact + unexpired Expires). Investigated: wellknown 100%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%.
- [fail] Schema coverage & depth — no .d.ts found. Investigated: sdk 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Self-service developer portal — Signup page at https://www.yelp.com/signup; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Changelog published — Newest official SDK activity 101 day(s) ago. Investigated: sdk 100%.
- [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.
- [skip] Description completeness — No surface produced evidence for this capability in this run.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (yelp/yelp-mcp, 417 snippets). Investigated: docs 100%, sdk 58%, cli 0%.
- [warn] llms.txt present, valid & comprehensive — No /llms-full.txt found at the candidate origins. Investigated: docs 71%, sdk 0%.
- [warn] Docs reachable, not hard auth-gated — 50 JavaScript redirect(s) detected across 50 sampled pages. Investigated: docs 50%.
- [warn] Crawlable / AEO — No sitemap discoverable via robots.txt or /sitemap.xml on the docs host. Investigated: wellknown 50%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Single base error "YelpError" with 11 subclasses. Investigated: sdk 100%.
- [warn] Agent-navigable, token-efficient docs — 2 of 50 pages have substantive content differences between markdown and HTML (avg 2% missing). Investigated: docs 75%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Operation purpose clarity — No surface produced evidence for this capability in this run.
- [skip] Docs structured data — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 1 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [warn] Sandbox separation — No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%.
- [fail] Idempotency documented — No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Yelp's API program shows meaningful strength in documentation discoverability and crawlability, but partners and their AI agents face two critical blockers: an incomplete, shallow API schema that makes it hard to build against with confidence, and a near-total absence of runnable, testable artifacts that agents need to integrate correctly. Closing the schema depth gap and providing executable, idempotency-documented workflows should be the immediate priority — these two areas most directly determine whether a partner (or the AI coding agent they use) can ship a working integration without hand-holding.