◎ Discry Score
paypal.com
payments · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 94 (A)
Discry your API →
PAYMENTS · RANK #13 OF 25

PayPal is Good to agents.

Discry independently scored how well an AI agent can discover and understand the PayPal API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 69/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Pass
llms-full.txtA full-text bundle agents can load in one request.Fail
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Partial
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 84/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Partial
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Pass
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Partial
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Partial

What we found

  • PayPal provides an llms.txt with a unique markdown-access hint: appending '/md/' before '/docs/' yields markdown versions of all pages, significantly improving agent consumption.
  • The robots.txt does not mention AI-specific bots (no GPTBot, ClaudeBot directives) — it neither explicitly blocks nor welcomes them, relying on the wildcard User-agent: * rule.
  • PayPal has an official Agent Toolkit (paypal/agent-toolkit) with dedicated MCP server support, listed on PulseMCP and Glama — strong agent tooling ecosystem.
  • Comprehensive per-API OpenAPI specs available on GitHub (paypal/paypal-rest-api-specifications) covering orders, payments, subscriptions, webhooks, and more.
  • Dedicated troubleshooting section with named error pages (agreement_already_cancelled, currency_mismatch, etc.) provides specific recovery guidance for common failure modes.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Add explicit AI bot directives to robots.txt (User-agent: GPTBot, ClaudeBot) to signal openness to agent crawling.
  2. 02Add llms-full.txt combining the core REST API documentation into a single comprehensive document.
  3. 03Add .well-known/mcp.json pointing to the official PayPal Agent Toolkit MCP server.
  4. 04Add AGENTS.md to the paypal/agent-toolkit or paypal-rest-api-specifications repos to guide coding agents.
  5. 05Consolidate the per-API OpenAPI specs into a single discoverable bundle or index document.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

OAuth2 (client credentials)Bearer token✓ Error format documented✓ Rate limits documented✓ Pagination documented✓ Idempotency documented

Well-documented execution characteristics including OAuth2 client credentials flow, structured JSON error responses with name/message/debug_id/details/links, dedicated rate limiting guidelines page, HATEOAS-based pagination, and idempotency key support.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free