◎ Discry Score
planetscale.com
infrastructure · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
INFRASTRUCTURE · RANK #48 OF 68

PlanetScale is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the PlanetScale 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 · 71/100
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.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.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 66/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Partial
Realistic examplesRunnable, real-world request/response examples.Partial
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Partial
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

  • PlanetScale's robots.txt explicitly signals AI-friendliness with Content-Signal: ai-train=yes, ai-input=yes — one of the strongest AI access signals in the infrastructure category
  • The llms.txt at planetscale.com/llms.txt is present and links to .md versions of all pages, but at 93.6KB it's a site-wide dump rather than a focused API summary — too large for efficient agent consumption
  • Strong MCP ecosystem presence: official MCP server listed on PulseMCP, Glama, and Smithery, plus a dedicated database-skills repo and VS Code agent plugin
  • OpenAPI 3.0 spec is publicly accessible and documented, giving agents structured access to the full API surface
  • Endpoint documentation is technically complete but descriptions focus heavily on authorization scopes rather than explaining what tasks each endpoint accomplishes

What to change

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

  1. 01Create a focused API-only llms.txt (<10KB) that covers core database management workflows — the current 93.6KB site-wide dump requires too many tokens for an agent to parse efficiently
  2. 02Add llms-full.txt with comprehensive API markdown content and .well-known/mcp.json with tool declarations to match the strong MCP registry presence
  3. 03Rewrite endpoint descriptions to lead with task context (e.g., 'Create a new isolated database branch for safe schema changes') before listing authorization requirements
  4. 04Add dedicated error recovery guidance for API errors (not just database errors) — show agents what to do when they receive 401, 403, 429, or 404 responses
  5. 05Add AGENTS.md to the primary planetscale/planetscale-go or database-skills repo with context on how coding agents should interact with the API

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.

service_tokenoauth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Service tokens and OAuth2 authentication well-documented. Rate limits documented with dedicated page. Both page-based and cursor-based pagination supported. No idempotency key documentation found.

See your own Discry Score.

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

Discry your API — free