# Mercury — API Agent Score

> Score: 81/100 (Grade: A) | Domain: mercury.com | Rubric: 1.0.0 | Checked: July 21, 2026

Mercury scored 81/100 (A), classified "ai-ready".

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

## Summary

- Overall: 81/100 (A)
- Classification: ai-ready

## Category Scores

- API Design: 98/100 (A+)
- Developer Experience: 68/100 (C)
- Agent Discovery: 79/100 (B)
- Agent Understanding: 84/100 (A)
- Agent Usability: 74/100 (B)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Versioning declared (info.version="1.0.0") and url-versioning detected. Investigated: spec 100%, docs 100%.
- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Schema coverage & depth — 41 of 633 public signatures use loose types (anyTypeRatio=0.065). Investigated: sdk 91%, spec 67%.
- [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] Self-service developer portal — Signup page at https://app.mercury.com/dashboard/signup; no free-tier language detected in docs/pricing. Investigated: docs 100%.
- [pass] Changelog published — Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.
- [warn] Description completeness — 21/39 operations lack a description. Investigated: sdk 46%, spec 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/mercury, 606 snippets). Investigated: docs 100%, sdk 100%, cli 0%, mcp 0%, wellknown 0%.
- [warn] llms.txt present, valid & comprehensive — No /llms-full.txt found at the candidate origins. Investigated: docs 86%, 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) — 4 distinct 4xx/5xx response codes documented. Investigated: spec 100%, docs 100%, sdk 100%.
- [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 — 50 of 51 endpoints have aggressive caching or missing cache headers. Investigated: docs 90%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (spec, sdk) is 9% (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 2 list endpoint(s). Investigated: docs 100%, sdk 95%, spec 75%.
- [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

Mercury's API design and documentation quality are clear strengths, giving partners a solid foundation to build against. The most critical gaps are in agent readiness and partner activation: there is no structured context file to guide AI agents operating on your API, and no runnable collection to let partners — or their agents — make a verified first call without guesswork. Prioritize closing these two gaps first, then sharpen onboarding and rate-limit signaling to ensure partners can reach production confidently and without surprises.