◎ Discry Score
elastic.com
infrastructure · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
INFRASTRUCTURE · RANK #24 OF 68

Elastic is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Elastic 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 · 83/100
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.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 · 78/100
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.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.Partial
Token efficiencyDocs are concise enough to fit an agent context window.Partial

What we found

  • Elastic has a well-structured llms.txt at /docs/llms.txt covering all three solution areas (Search, Observability, Security) with clear descriptions and links — and the quality is genuinely agent-useful
  • The elastic/agent-skills repository represents a best-in-class approach to agent readiness — curated SKILL.md files that teach AI agents how to work with Elasticsearch, Kibana, and Elastic Security
  • Official MCP server (elastic/mcp-server-elasticsearch) on GitHub, Glama, and PulseMCP enables natural language queries against Elasticsearch indices
  • robots.txt is extremely granular with hundreds of Allow/Disallow rules — while not blocking AI bots specifically, the restrictive default posture means many doc pages are disallowed
  • OpenAPI specification is generated from the elasticsearch-specification repo and the generated output is publicly available on GitHub

What to change

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

  1. 01Add llms-full.txt at /docs/llms-full.txt with comprehensive markdown content covering core Elasticsearch API operations
  2. 02Add .well-known/mcp.json pointing to the official MCP server with tool declarations and auth configuration
  3. 03Simplify robots.txt — the current hundreds of granular rules make it difficult for any crawler; consider a more permissive default for /docs/ paths
  4. 04Add per-endpoint error recovery guidance beyond standard HTTP status codes — current docs lack actionable fix steps for common errors
  5. 05Document rate limits for Elastic Cloud API endpoints to help agents handle throttling gracefully

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_keybasic_authoauth2✓ Error format documented✕ Rate limits documented✓ Pagination documented✕ Idempotency documented

API key and Basic auth for Elasticsearch, OAuth2 for Elastic Cloud. JSON error responses with structured error objects. Pagination via search_after cursor and scroll API. No explicit rate limit documentation for self-managed; Cloud has usage-based limits. No idempotency key support documented.

See your own Discry Score.

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

Discry your API — free