◎ Discry Score
stytch.com
auth · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 93 (A)
Discry your API →
AUTH · RANK #3 OF 16

Stytch is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Stytch 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 · 81/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Partial
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Partial
llms-full.txtA full-text bundle agents can load in one request.Partial
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Pass
.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.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 96/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
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.Partial
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.Pass
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.Pass

What we found

  • Stytch has the most developer-friendly LLM integration of any API scanned: dedicated 'LLM instructions' page, 'Copy page as Markdown', 'Open in ChatGPT/Claude' on every page, and Documentation Index callout everywhere
  • The llms.txt and llms-full.txt files are referenced prominently but require OAuth authentication to access directly — a significant agent-discovery gap since automated agents cannot complete OAuth flows to read documentation
  • Stytch has official OpenAPI specs for both the core auth API (stytchauth/stytch-openapi) and the Management API (stytch-management-openapi), plus an official MCP server with OAuth flow built in
  • The 'AI agents & apps' and 'Connected Apps' documentation sections show deliberate investment in the agent economy — Stytch is positioning as auth infrastructure for AI agents
  • Code examples use realistic values with environment-prefixed IDs (member-test-16d9ba61...) across 6 SDK languages, making them highly copy-pasteable

What to change

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

  1. 01Make llms.txt publicly accessible without OAuth authentication — gating documentation discovery behind auth defeats the purpose for automated agents
  2. 02Add .well-known/mcp.json advertising the official Stytch MCP server capabilities
  3. 03The authentication gate on llms.txt is the single biggest score-limiting factor — removing it would likely push discovery from C to A grade
  4. 04Consider adding rate limit documentation to public-facing pages (currently may be behind auth)

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.

api_keyoauth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Basic authentication with project_id and secret. Separate test (test.stytch.com) and live (api.stytch.com) environments. JSON responses. Error codes documented with dedicated Errors section in API reference. Sandbox values for testing. Backend SDKs for Node, Python, Ruby, Go, Java. No idempotency keys mentioned.

See your own Discry Score.

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

Discry your API — free