◎ Discry Score
clerk.com
auth · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 93 (A)
Discry your API →
AUTH · RANK #5 OF 16

Clerk is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Clerk 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 · 86/100
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.Partial
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.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 · 87/100
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.Partial
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.Partial

What we found

  • Clerk has invested heavily in agent tooling — AGENTS.md in clerk/skills repo, Agent Toolkit package, MCP servers, and Skills covering 18 categories across frameworks
  • The llms.txt is 328KB which is too large for efficient agent consumption — it includes blog posts, changelog entries, and marketing content alongside API documentation
  • No .well-known/mcp.json despite having an official MCP server and agent toolkit — agents must discover these through external registries
  • Quickstart guides are exemplary for multi-step workflows: create app → install → set keys → add middleware → add provider → run
  • OpenAPI specs are publicly available at github.com/clerk/openapi-specs with Frontend, Backend, and Platform API specs

What to change

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

  1. 01Create a focused llms.txt under 50KB that covers only the Backend API and SDK integration patterns, not blog/changelog content
  2. 02Add .well-known/mcp.json pointing to the official Clerk MCP server with tool declarations
  3. 03Add llms-full.txt at clerk.com/llms-full.txt with the comprehensive documentation in markdown format
  4. 04Add error recovery guidance with specific fix steps for common auth errors (token expired, invalid redirect URI, etc.)

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_keyoauth2jwt✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Well-documented execution characteristics. Bearer token auth with secret keys, versioned API with release dates, JSON error responses. Rate limits and pagination documented. No idempotency support mentioned.

See your own Discry Score.

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

Discry your API — free