◎ Discry Score
splunk.com
infrastructure · API
F
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
INFRASTRUCTURE · RANK #64 OF 68

Splunk is Not Agent-Ready to agents.

Discry independently scored how well an AI agent can discover and understand the Splunk 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 · 26/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Partial
llms.txtAn llms.txt index that points agents to the docs that matter.Fail
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Fail
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.Fail
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 50/100
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.Partial
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Partial
Heading hierarchyClean heading structure agents can navigate.Partial
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Partial
Token efficiencyDocs are concise enough to fit an agent context window.Fail

What we found

  • Splunk has strong MCP registry presence with an official server on PulseMCP plus community servers on Glama and Smithery for SPL query execution
  • The developer portal at dev.splunk.com renders entirely via JavaScript — robots.txt and llms.txt both return HTML/JS instead of plain text
  • An OpenAPI spec exists only for the Splunk Cloud ACS API, not the broader Enterprise REST API
  • Multiple community MCP servers enable natural language to SPL query translation, showing strong agent demand
  • Documentation is extensive but scattered across Enterprise, Cloud, and Observability products

What to change

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

  1. 01Fix dev.splunk.com to serve robots.txt and llms.txt as proper plain text files
  2. 02Create a unified OpenAPI spec for the Splunk Enterprise REST API
  3. 03Add llms.txt covering core search, indexing, and admin API capabilities
  4. 04Consolidate documentation across Enterprise/Cloud/Observability for consistent agent consumption
  5. 05Add .well-known/mcp.json pointing to the official Splunk MCP server

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 keyOAuth2session token✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Splunk uses session tokens, API keys, and OAuth2. JSON/XML error responses. Rate limits for Cloud ACS API documented. Pagination varies by endpoint.

See your own Discry Score.

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

Discry your API — free