◎ Discry Score
sanity.com
cms · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 96 (A)
Discry your API →
CMS · RANK #7 OF 13

Sanity is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Sanity 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 · 67/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Partial
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.Partial
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

  • Sanity has the deepest agent-first investment in the CMS category: dedicated AI documentation section, agent-toolkit repo with AGENTS.md, agent-context repo, Agent Skills, MCP server with OAuth, and Content Agent API — this is category-leading
  • AGENTS.md is present in multiple repos (agent-toolkit, agent-context, plugins) acting as a 'Knowledge Router' that directs coding agents to relevant reference files for specific tasks — a novel and effective pattern
  • 20 OpenAPI specs covering every API surface (Query, Mutation, Assets, History, etc.) are available via the Sanity CLI — though not directly at a web URL, this is the most comprehensive spec coverage in the cohort
  • The llms.txt at sanity.io/llms.txt is well-structured with an AI-focused section covering MCP setup, Agent Skills, and Content Agent API — showing the AI docs are first-class citizens
  • robots.txt uses Content-Signal with ai-train=no, ai-input=no — same pattern as Render, allowing agent access while restricting training use

What to change

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

  1. 01Publish OpenAPI specs at a public URL (e.g., sanity.io/docs/openapi/query.json) rather than only via CLI — agents cannot run `sanity openapi get` to discover the API
  2. 02Add .well-known/mcp.json at sanity.io pointing to the hosted MCP server at mcp.sanity.io — connects the excellent MCP infrastructure to a standard discovery path
  3. 03Add llms-full.txt at sanity.io/llms-full.txt combining the complete documentation into a single markdown file for deep agent comprehension
  4. 04Add dedicated API error recovery documentation for HTTP API errors (authentication failures, rate limits, malformed queries) with specific recovery steps

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

Robot tokens and bearer token authentication. GROQ query language for content retrieval with CDN endpoint for edge caching. OpenAPI specs available for 20 API surfaces via CLI. GET query limit of 11KB (use POST for larger). JSON responses with ms timing. Cursor-based pagination available. Request tags for log filtering.

See your own Discry Score.

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

Discry your API — free